Is it a request payload issue?
Yes, this is a request payload issue. I am using a client/cURL to send a request payload, but I received an unexpected error.
If it's a request payload issue, you MUST know
Our team doesn't have any GODs or ORACLEs or MIND READERs. Please make sure to attach the request log or curl payload.
Describe the bug
Can not work with mcp:ncp on antigravity-provider
CLI Type
claude code,opencode
Model Name
gemini-3.0-pro-high,claude-sonnet-4-thinking and so on
LLM Client
claude code,opencode
Request Information
O: 22O: 22
904ms 22:59:23904ms 22:59:23
400 POST claude-sonnet-4-5 /v1/messages?beta=true 305ms 22:59:23
400 POST claude-sonnet-4-5 /v1/messages?beta=true 305ms 22:59:23
400 POST claude-sonnet-4-5 /v1/messages?beta=true 469ms 22:59:22
400 POST claude-sonnet-4-5 /v1/messages?beta=true 469ms 22:59:22
200 POST gemini-3-flash /v1/messages?beta=true
200 POST gemini-3-flash /v1/messages?beta=true
I: 465I: 465
O: 20O: 20
8893ms 22:58:528893ms 22:58:52
200 POST gemini-3-flash /v1/messages?beta=true
200 POST gemini-3-flash /v1/messages?beta=true
I: 4.3kI: 4.3k
O: 106O: 106
3665ms 22:58:473665ms 22:58:47
200 POST claude-sonnet-4-5 /v1/messages?beta=true
200 POST claude-sonnet-4-5 /v1/messages?beta=true
I: 5.9kI: 5.9k
O: 158O: 158
3017ms 22:58:463017ms 22:58:46
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 1ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 1ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST gemini-3-flash /v1/messages?beta=true
I: 6k
O: 138
5780ms 22:57:16
200 POST claude-sonnet-4-5 /v1/messages?beta=true
I: 7.8k
O: 107
4908ms 22:57:15
400 POST claude-sonnet-4-5 /v1/messages?beta=true 377ms 22:57:14
200 POST gemini-3-flash /v1/messages?beta=true
I: 194
O: 19
3138ms 22:57:14
400 POST claude-sonnet-4-5 /v1/messages?beta=true 2757ms 22:57:14
404 POST claude-sonnet-4-5 /v1/messages/v1/messages?beta=true 0ms 22:56:38
404 POST claude-sonnet-4-5 /v1/messages/v1/messages?beta=true 1ms 22:56:38
404 POST gemini-3-flash /v1/messages/v1/messages?beta=true 0ms 22:56:38
404 POST gemini-3-flash /v1/messages/v1/messages?beta=true 0ms 22:56:38
400
POST
/v1/messages?beta=true
请求时间
2026/1/5 22:59:23
耗时
305ms
TOKEN 消耗 (输入/输出)
In: 0
Out: 0
使用模型
claude-sonnet-4-5
请求报文 (REQUEST)
{
"model": "claude-sonnet-4-5",
"messages": [
{
"role": "user",
"content": [
{
{
"name": "mcp__plugin_claude-mem_mcp-search____IMPORTANT",
"description": "3-LAYER WORKFLOW (ALWAYS FOLLOW):\n1. search(query) → Get index with IDs (~50-100 tokens/result)\n2. timeline(anchor=ID) → Get context around interesting results\n3. get_observations([IDs]) → Fetch full details ONLY for filtered IDs\nNEVER fetch full details without filtering first.
10x token savings.",
"input_schema": {
"type": "object",
"properties": {}
}
},
{
"name": "mcp__plugin_claude-mem_mcp-search__search",
"description": "Step 1: Search memory.
Returns index with IDs.
Params: query, limit, project, type, obs_type, dateStart, dateEnd, offset, orderBy",
"input_schema": {
"type": "object",
"properties": {},
"additionalProperties": true
}
},
{
"name": "mcp__plugin_claude-mem_mcp-search__timeline",
"description": "Step 2: Get context around results.
Params: anchor (observation ID) OR query (finds anchor automatically), depth_before, depth_after, project",
"input_schema": {
"type": "object",
"properties": {},
"additionalProperties": true
}
},
{
"name": "mcp__plugin_claude-mem_mcp-search__get_observations",
"description": "Step 3: Fetch full details for filtered IDs.
Params: ids (array of observation IDs, required), orderBy, limit, project",
"input_schema": {
"type": "object",
"properties": {
"ids": {
"type": "array",
"items": {
"type": "number"
},
"description": "Array of observation IDs to fetch (required)"
}
},
"required": [
"ids"
],
"additionalProperties": true
}
},
{
"name": "mcp__Ncp__find",
"description": "Search or list MCP tools.
Call as find() - no prefix needed.
With description param: vector search tools by capability.
Without description: list all available tools.
Use pipe separator for multi-query ("gmail | slack").",
"input_schema": {
"type": "object",
"properties": {
"description": {
"type": "string",
"description": "Search query describing capability you need (e.g.
"send email", "read file").
OMIT this parameter entirely to list all tools (do not pass "list all" or empty string).
Use pipe separator for multi-query ("gmail | slack")."
},
"limit": {
"type": "number",
"description": "Max results per page (default: 5 search, 20 list)"
},
"page": {
"type": "number",
"description": "Page number (default: 1)"
},
"confidence_threshold": {
"type": "number",
"description": "Min confidence 0.0-1.0 (default: 0.35).
Lower=more results, higher=precise."
},
"depth": {
"type": "number",
"description": "Detail level: 0=names, 1=+descriptions, 2=+parameters (default: 2)",
"enum": [
0,
1,
2
]
}
}
}
},
{
"name": "mcp__Ncp__code",
"description": "Execute TypeScript with MCPs as namespaces (e.g., github.get_repo()).
Use ncp.find() for discovery.
Console captured.",
"input_schema": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "TypeScript code.
MCPs available as namespaces.
Example: await gmail.send_email({to, subject, body})"
},
"timeout": {
"type": "number",
"description": "Timeout in ms (default: 30000, max: 300000)"
}
},
"required": [
"code"
]
}
},
{
"name": "ListMcpResourcesTool",
"description": "\nList available resources from configured MCP servers.\nEach returned resource will include all standard MCP resource fields plus a 'server' field \nindicating which server the resource belongs to.\n\nParameters:\n- server (optional): The name of a specific MCP server to get resources from.
If not provided,\n resources from all servers will be returned.\n",
"input_schema": {
"type": "object",
"properties": {
"server": {
"type": "string",
"description": "Optional server name to filter resources by"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "ReadMcpResourceTool",
"description": "\nReads a specific resource from an MCP server, identified by server name and resource URI.\n\nParameters:\n- server (required): The name of the MCP server from which to read the resource\n- uri (required): The URI of the resource to read\n",
"input_schema": {
"type": "object",
"properties": {
"server": {
"type": "string",
"description": "The MCP server name"
},
"uri": {
"type": "string",
"description": "The resource URI to read"
}
},
"required": [
"server",
"uri"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__ui_to_artifact",
"description": "Convert UI screenshots into various artifacts: code, prompts, design specifications, or descriptions.\n\nUse this tool ONLY when the user wants to:\n- Generate frontend code from UI design (output_type='code')\n- Create AI prompts for UI generation (output_type='prompt')\n- Extract design specifications (output_type='spec')\n- Get natural language description of the UI (output_type='description')\n\nDo NOT use for: screenshots containing text/code to extract, error messages, diagrams, or data visualizations.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"output_type": {
"type": "string",
"enum": [
"code",
"prompt",
"spec",
"description"
],
"description": "Type of output to generate.
Options: 'code' (generate frontend code), 'prompt' (generate AI prompt for recreating this UI), 'spec' (generate design specification document), 'description' (natural language description of the UI)."
},
"prompt": {
"type": "string",
"description": "Detailed instructions describing what to generate from this UI image.
Should clearly state the desired output and any specific requirements."
}
},
"required": [
"image_source",
"output_type",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__extract_text_from_screenshot",
"description": "Extract and recognize text from screenshots using advanced OCR capabilities.\n\nUse this tool ONLY when the user has a screenshot containing text and wants to extract it.\nThis tool specializes in OCR for code, terminal output, documentation, and general text extraction.\n\nDo NOT use for: UI design conversion, error diagnosis, or diagram understanding.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "Instructions for text extraction.
Specify what type of text to extract and any formatting requirements."
},
"programming_language": {
"type": "string",
"description": "Optional: specify the programming language if the screenshot contains code (e.g., 'python', 'javascript', 'java').
Leave empty for auto-detection or non-code text."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__diagnose_error_screenshot",
"description": "Diagnose and analyze error messages, stack traces, and exception screenshots.\n\nUse this tool ONLY when the user has an error screenshot and needs help understanding or fixing it.\nThis tool specializes in error analysis and provides actionable solutions.\n\nDo NOT use for: code extraction, UI analysis, or diagram understanding.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "Description of what you need help with regarding this error.
Include any relevant context about when it occurred."
},
"context": {
"type": "string",
"description": "Optional: additional context about when the error occurred (e.g., 'during npm install', 'when running the app', 'after deployment').
Helps with more accurate diagnosis."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__understand_technical_diagram",
"description": "Analyze and explain technical diagrams including architecture diagrams, flowcharts, UML, ER diagrams, and system design diagrams.\n\nUse this tool ONLY when the user has a technical diagram and wants to understand its structure or components.\nThis tool specializes in interpreting visual technical documentation.\n\nDo NOT use for: UI screenshots, error messages, or data visualizations/charts.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "What you want to understand or extract from this diagram."
},
"diagram_type": {
"type": "string",
"description": "Optional: specify the diagram type if known (e.g., 'architecture', 'flowchart', 'uml', 'er-diagram', 'sequence').
Leave empty for auto-detection."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__analyze_data_visualization",
"description": "Analyze data visualizations, charts, graphs, and dashboards to extract insights and trends.\n\nUse this tool ONLY when the user has a data visualization image and wants to understand the data patterns or metrics.\nThis tool specializes in interpreting visual data representations.\n\nDo NOT use for: UI mockups, error messages, or technical architecture diagrams.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "What insights or information you want to extract from this visualization."
},
"analysis_focus": {
"type": "string",
"description": "Optional: specify what to focus on (e.g., 'trends', 'anomalies', 'comparisons', 'performance metrics').
Leave empty for comprehensive analysis."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__ui_diff_check",
"description": "Compare two UI screenshots to identify visual differences and implementation discrepancies.\n\nUse this tool ONLY when the user wants to compare an expected/reference UI with an actual implementation.\nThis tool is specialized for UI quality assurance and design-to-implementation verification.\n\nDo NOT use for: general image comparison, error diagnosis, or analyzing single UIs.",
"input_schema": {
"type": "object",
"properties": {
"expected_image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"actual_image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "Instructions for the comparison.
Specify what aspects to focus on or what level of detail is needed."
}
},
"required": [
"expected_image_source",
"actual_image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__analyze_image",
"description": "General-purpose image analysis for scenarios not covered by specialized tools.\n\nUse this tool as a FALLBACK when none of the other specialized tools (ui_to_artifact, extract_text_from_screenshot,\ndiagnose_error_screenshot, understand_technical_diagram, analyze_data_visualization, ui_diff_check) fit the user's need.\n\nThis tool provides flexible image understanding for any visual content.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "Detailed description of what you want to analyze, extract, or understand from the image.
Be specific about your requirements."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__analyze_video",
"description": "Analyze video content using advanced AI vision models.\n\nUse this tool when the user wants to:\n- Understand what happens in a video\n- Extract key moments or actions from video\n- Analyze video content, scenes, or sequences\n- Get descriptions of video footage\n- Identify objects, people, or activities in video\n\nSupports both local files and remote URL.
Maximum file size: 8MB.
Supports MP4, MOV, M4V formats.",
"input_schema": {
"type": "object",
"properties": {
"video_source": {
"type": "string",
"description": "Local file path or remote URL to the video (supports MP4, MOV, M4V)"
},
"prompt": {
"type": "string",
"description": "Detailed text prompt describing what to analyze, extract, or understand from the video"
}
},
"required": [
"video_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
],
"metadata": {
"user_id": "user_d6b6459ffe853fa1da6907353ee940124a6a9bd7fa071b0fd9421af648cf05e7_account__session_ab777f87-8699-4269-bc6f-5c4e39bf4436"
},
"max_tokens": 21333,
"thinking": {
"budget_tokens": 21332,
"type": "enabled"
},
"temperature": 1
}
响应报文 (RESPONSE)
{
"error": {
"code": 400,
"message": "Invalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[0]' (TYPE_STRING), 0\nInvalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[1]' (TYPE_STRING), 1\nInvalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[2]' (TYPE_STRING), 2",
"status": "INVALID_ARGUMENT",
"details": [
{
"@type": "type.googleapis.com/google.rpc.BadRequest",
"fieldViolations": [
{
"field": "request.tools[0].function_declarations[22].parameters.properties[1].value.enum[0]",
"description": "Invalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[0]' (TYPE_STRING), 0"
},
{
"field": "request.tools[0].function_declarations[22].parameters.properties[1].value.enum[1]",
"description": "Invalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[1]' (TYPE_STRING), 1"
},
{
"field": "request.tools[0].function_declarations[22].parameters.properties[1].value.enum[2]",
"description": "Invalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[2]' (TYPE_STRING), 2"
}
]
}
]
}
}
Expected behavior
A clear and concise description of what you expected to happen.
Screenshots
If applicable, add screenshots to help explain your problem.
OS Type
- OS: [e.g. macOS]
- Version [e.g. 15.6.0]
Additional context
在启用ncp这个mcp之后，使用antigravity得api会报错
使用这个ncp后用codex、claude接glm4.7等可以正常使用
Antigravity Tools
仪表盘
账号管理
API 反代
设置
中
API 监控看板
实时请求日志与分析
30 REQS30 REQS
22 OK22 OK
8 ERR8 ERR
快速过滤:快速过滤:
全部全部
仅错误仅错误
聊天聊天
GeminiGemini
ClaudeClaude
绘图绘图
状态 方法 模型 路径 Token 消耗 耗时 时间
状态 方法 模型 路径 Token 消耗 耗时 时间
200 POST gemini-3-flash /v1/messages?beta=true
200 POST gemini-3-flash /v1/messages?beta=true
I: 650I: 650
O: 22O: 22
904ms 22:59:23904ms 22:59:23
400 POST claude-sonnet-4-5 /v1/messages?beta=true 305ms 22:59:23
400 POST claude-sonnet-4-5 /v1/messages?beta=true 305ms 22:59:23
400 POST claude-sonnet-4-5 /v1/messages?beta=true 469ms 22:59:22
400 POST claude-sonnet-4-5 /v1/messages?beta=true 469ms 22:59:22
200 POST gemini-3-flash /v1/messages?beta=true
200 POST gemini-3-flash /v1/messages?beta=true
I: 465I: 465
O: 20O: 20
8893ms 22:58:528893ms 22:58:52
200 POST gemini-3-flash /v1/messages?beta=true
200 POST gemini-3-flash /v1/messages?beta=true
I: 4.3kI: 4.3k
O: 106O: 106
3665ms 22:58:473665ms 22:58:47
200 POST claude-sonnet-4-5 /v1/messages?beta=true
200 POST claude-sonnet-4-5 /v1/messages?beta=true
I: 5.9kI: 5.9k
O: 158O: 158
3017ms 22:58:463017ms 22:58:46
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 1ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 1ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST gemini-3-flash /v1/messages?beta=true
I: 6k
O: 138
5780ms 22:57:16
200 POST claude-sonnet-4-5 /v1/messages?beta=true
I: 7.8k
O: 107
4908ms 22:57:15
400 POST claude-sonnet-4-5 /v1/messages?beta=true 377ms 22:57:14
200 POST gemini-3-flash /v1/messages?beta=true
I: 194
O: 19
3138ms 22:57:14
400 POST claude-sonnet-4-5 /v1/messages?beta=true 2757ms 22:57:14
404 POST claude-sonnet-4-5 /v1/messages/v1/messages?beta=true 0ms 22:56:38
404 POST claude-sonnet-4-5 /v1/messages/v1/messages?beta=true 1ms 22:56:38
404 POST gemini-3-flash /v1/messages/v1/messages?beta=true 0ms 22:56:38
404 POST gemini-3-flash /v1/messages/v1/messages?beta=true 0ms 22:56:38
400
POST
/v1/messages?beta=true
请求时间
2026/1/5 22:59:23
耗时
305ms
TOKEN 消耗 (输入/输出)
In: 0
Out: 0
使用模型
claude-sonnet-4-5
请求报文 (REQUEST)
{
"model": "claude-sonnet-4-5",
"messages": [
{
"role": "user",
"content": [
{
{
"name": "mcp__plugin_claude-mem_mcp-search____IMPORTANT",
"description": "3-LAYER WORKFLOW (ALWAYS FOLLOW):\n1. search(query) → Get index with IDs (~50-100 tokens/result)\n2. timeline(anchor=ID) → Get context around interesting results\n3. get_observations([IDs]) → Fetch full details ONLY for filtered IDs\nNEVER fetch full details without filtering first.
10x token savings.",
"input_schema": {
"type": "object",
"properties": {}
}
},
{
"name": "mcp__plugin_claude-mem_mcp-search__search",
"description": "Step 1: Search memory.
Returns index with IDs.
Params: query, limit, project, type, obs_type, dateStart, dateEnd, offset, orderBy",
"input_schema": {
"type": "object",
"properties": {},
"additionalProperties": true
}
},
{
"name": "mcp__plugin_claude-mem_mcp-search__timeline",
"description": "Step 2: Get context around results.
Params: anchor (observation ID) OR query (finds anchor automatically), depth_before, depth_after, project",
"input_schema": {
"type": "object",
"properties": {},
"additionalProperties": true
}
},
{
"name": "mcp__plugin_claude-mem_mcp-search__get_observations",
"description": "Step 3: Fetch full details for filtered IDs.
Params: ids (array of observation IDs, required), orderBy, limit, project",
"input_schema": {
"type": "object",
"properties": {
"ids": {
"type": "array",
"items": {
"type": "number"
},
"description": "Array of observation IDs to fetch (required)"
}
},
"required": [
"ids"
],
"additionalProperties": true
}
},
{
"name": "mcp__Ncp__find",
"description": "Search or list MCP tools.
Call as find() - no prefix needed.
With description param: vector search tools by capability.
Without description: list all available tools.
Use pipe separator for multi-query ("gmail | slack").",
"input_schema": {
"type": "object",
"properties": {
"description": {
"type": "string",
"description": "Search query describing capability you need (e.g.
"send email", "read file").
OMIT this parameter entirely to list all tools (do not pass "list all" or empty string).
Use pipe separator for multi-query ("gmail | slack")."
},
"limit": {
"type": "number",
"description": "Max results per page (default: 5 search, 20 list)"
},
"page": {
"type": "number",
"description": "Page number (default: 1)"
},
"confidence_threshold": {
"type": "number",
"description": "Min confidence 0.0-1.0 (default: 0.35).
Lower=more results, higher=precise."
},
"depth": {
"type": "number",
"description": "Detail level: 0=names, 1=+descriptions, 2=+parameters (default: 2)",
"enum": [
0,
1,
2
]
}
}
}
},
{
"name": "mcp__Ncp__code",
"description": "Execute TypeScript with MCPs as namespaces (e.g., github.get_repo()).
Use ncp.find() for discovery.
Console captured.",
"input_schema": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "TypeScript code.
MCPs available as namespaces.
Example: await gmail.send_email({to, subject, body})"
},
"timeout": {
"type": "number",
"description": "Timeout in ms (default: 30000, max: 300000)"
}
},
"required": [
"code"
]
}
},
{
"name": "ListMcpResourcesTool",
"description": "\nList available resources from configured MCP servers.\nEach returned resource will include all standard MCP resource fields plus a 'server' field \nindicating which server the resource belongs to.\n\nParameters:\n- server (optional): The name of a specific MCP server to get resources from.
If not provided,\n resources from all servers will be returned.\n",
"input_schema": {
"type": "object",
"properties": {
"server": {
"type": "string",
"description": "Optional server name to filter resources by"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "ReadMcpResourceTool",
"description": "\nReads a specific resource from an MCP server, identified by server name and resource URI.\n\nParameters:\n- server (required): The name of the MCP server from which to read the resource\n- uri (required): The URI of the resource to read\n",
"input_schema": {
"type": "object",
"properties": {
"server": {
"type": "string",
"description": "The MCP server name"
},
"uri": {
"type": "string",
"description": "The resource URI to read"
}
},
"required": [
"server",
"uri"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__ui_to_artifact",
"description": "Convert UI screenshots into various artifacts: code, prompts, design specifications, or descriptions.\n\nUse this tool ONLY when the user wants to:\n- Generate frontend code from UI design (output_type='code')\n- Create AI prompts for UI generation (output_type='prompt')\n- Extract design specifications (output_type='spec')\n- Get natural language description of the UI (output_type='description')\n\nDo NOT use for: screenshots containing text/code to extract, error messages, diagrams, or data visualizations.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"output_type": {
"type": "string",
"enum": [
"code",
"prompt",
"spec",
"description"
],
"description": "Type of output to generate.
Options: 'code' (generate frontend code), 'prompt' (generate AI prompt for recreating this UI), 'spec' (generate design specification document), 'description' (natural language description of the UI)."
},
"prompt": {
"type": "string",
"description": "Detailed instructions describing what to generate from this UI image.
Should clearly state the desired output and any specific requirements."
}
},
"required": [
"image_source",
"output_type",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__extract_text_from_screenshot",
"description": "Extract and recognize text from screenshots using advanced OCR capabilities.\n\nUse this tool ONLY when the user has a screenshot containing text and wants to extract it.\nThis tool specializes in OCR for code, terminal output, documentation, and general text extraction.\n\nDo NOT use for: UI design conversion, error diagnosis, or diagram understanding.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "Instructions for text extraction.
Specify what type of text to extract and any formatting requirements."
},
"programming_language": {
"type": "string",
"description": "Optional: specify the programming language if the screenshot contains code (e.g., 'python', 'javascript', 'java').
Leave empty for auto-detection or non-code text."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__diagnose_error_screenshot",
"description": "Diagnose and analyze error messages, stack traces, and exception screenshots.\n\nUse this tool ONLY when the user has an error screenshot and needs help understanding or fixing it.\nThis tool specializes in error analysis and provides actionable solutions.\n\nDo NOT use for: code extraction, UI analysis, or diagram understanding.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "Description of what you need help with regarding this error.
Include any relevant context about when it occurred."
},
"context": {
"type": "string",
"description": "Optional: additional context about when the error occurred (e.g., 'during npm install', 'when running the app', 'after deployment').
Helps with more accurate diagnosis."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__understand_technical_diagram",
"description": "Analyze and explain technical diagrams including architecture diagrams, flowcharts, UML, ER diagrams, and system design diagrams.\n\nUse this tool ONLY when the user has a technical diagram and wants to understand its structure or components.\nThis tool specializes in interpreting visual technical documentation.\n\nDo NOT use for: UI screenshots, error messages, or data visualizations/charts.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "What you want to understand or extract from this diagram."
},
"diagram_type": {
"type": "string",
"description": "Optional: specify the diagram type if known (e.g., 'architecture', 'flowchart', 'uml', 'er-diagram', 'sequence').
Leave empty for auto-detection."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__analyze_data_visualization",
"description": "Analyze data visualizations, charts, graphs, and dashboards to extract insights and trends.\n\nUse this tool ONLY when the user has a data visualization image and wants to understand the data patterns or metrics.\nThis tool specializes in interpreting visual data representations.\n\nDo NOT use for: UI mockups, error messages, or technical architecture diagrams.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "What insights or information you want to extract from this visualization."
},
"analysis_focus": {
"type": "string",
"description": "Optional: specify what to focus on (e.g., 'trends', 'anomalies', 'comparisons', 'performance metrics').
Leave empty for comprehensive analysis."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__ui_diff_check",
"description": "Compare two UI screenshots to identify visual differences and implementation discrepancies.\n\nUse this tool ONLY when the user wants to compare an expected/reference UI with an actual implementation.\nThis tool is specialized for UI quality assurance and design-to-implementation verification.\n\nDo NOT use for: general image comparison, error diagnosis, or analyzing single UIs.",
"input_schema": {
"type": "object",
"properties": {
"expected_image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"actual_image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "Instructions for the comparison.
Specify what aspects to focus on or what level of detail is needed."
}
},
"required": [
"expected_image_source",
"actual_image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__analyze_image",
"description": "General-purpose image analysis for scenarios not covered by specialized tools.\n\nUse this tool as a FALLBACK when none of the other specialized tools (ui_to_artifact, extract_text_from_screenshot,\ndiagnose_error_screenshot, understand_technical_diagram, analyze_data_visualization, ui_diff_check) fit the user's need.\n\nThis tool provides flexible image understanding for any visual content.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "Detailed description of what you want to analyze, extract, or understand from the image.
Be specific about your requirements."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__analyze_video",
"description": "Analyze video content using advanced AI vision models.\n\nUse this tool when the user wants to:\n- Understand what happens in a video\n- Extract key moments or actions from video\n- Analyze video content, scenes, or sequences\n- Get descriptions of video footage\n- Identify objects, people, or activities in video\n\nSupports both local files and remote URL.
Maximum file size: 8MB.
Supports MP4, MOV, M4V formats.",
"input_schema": {
"type": "object",
"properties": {
"video_source": {
"type": "string",
"description": "Local file path or remote URL to the video (supports MP4, MOV, M4V)"
},
"prompt": {
"type": "string",
"description": "Detailed text prompt describing what to analyze, extract, or understand from the video"
}
},
"required": [
"video_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
],
"metadata": {
"user_id": "user_d6b6459ffe853fa1da6907353ee940124a6a9bd7fa071b0fd9421af648cf05e7_account__session_ab777f87-8699-4269-bc6f-5c4e39bf4436"
},
"max_tokens": 21333,
"thinking": {
"budget_tokens": 21332,
"type": "enabled"
},
"temperature": 1
}
响应报文 (RESPONSE)
{
"error": {
"code": 400,
"message": "Invalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[0]' (TYPE_STRING), 0\nInvalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[1]' (TYPE_STRING), 1\nInvalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[2]' (TYPE_STRING), 2",
"status": "INVALID_ARGUMENT",
"details": [
{
"@type": "type.googleapis.com/google.rpc.BadRequest",
"fieldViolations": [
{
"field": "request.tools[0].function_declarations[22].parameters.properties[1].value.enum[0]",
"description": "Invalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[0]' (TYPE_STRING), 0"
},
{
"field": "request.tools[0].function_declarations[22].parameters.properties[1].value.enum[1]",
"description": "Invalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[1]' (TYPE_STRING), 1"
},
{
"field": "request.tools[0].function_declarations[22].parameters.properties[1].value.enum[2]",
"description": "Invalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[2]' (TYPE_STRING), 2"
}
]
}
]
}
}
Is it a request payload issue?
Yes, this is a request payload issue. I am using a client/cURL to send a request payload, but I received an unexpected error.
If it's a request payload issue, you MUST know
Our team doesn't have any GODs or ORACLEs or MIND READERs. Please make sure to attach the request log or curl payload.
Describe the bug
Can not work with mcp:ncp on antigravity-provider
CLI Type
claude code,opencode
Model Name
gemini-3.0-pro-high,claude-sonnet-4-thinking and so on
LLM Client
claude code,opencode
Request Information
O: 22O: 22
904ms 22:59:23904ms 22:59:23
400 POST claude-sonnet-4-5 /v1/messages?beta=true 305ms 22:59:23
400 POST claude-sonnet-4-5 /v1/messages?beta=true 305ms 22:59:23
400 POST claude-sonnet-4-5 /v1/messages?beta=true 469ms 22:59:22
400 POST claude-sonnet-4-5 /v1/messages?beta=true 469ms 22:59:22
200 POST gemini-3-flash /v1/messages?beta=true
200 POST gemini-3-flash /v1/messages?beta=true
I: 465I: 465
O: 20O: 20
8893ms 22:58:528893ms 22:58:52
200 POST gemini-3-flash /v1/messages?beta=true
200 POST gemini-3-flash /v1/messages?beta=true
I: 4.3kI: 4.3k
O: 106O: 106
3665ms 22:58:473665ms 22:58:47
200 POST claude-sonnet-4-5 /v1/messages?beta=true
200 POST claude-sonnet-4-5 /v1/messages?beta=true
I: 5.9kI: 5.9k
O: 158O: 158
3017ms 22:58:463017ms 22:58:46
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 1ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 1ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST gemini-3-flash /v1/messages?beta=true
I: 6k
O: 138
5780ms 22:57:16
200 POST claude-sonnet-4-5 /v1/messages?beta=true
I: 7.8k
O: 107
4908ms 22:57:15
400 POST claude-sonnet-4-5 /v1/messages?beta=true 377ms 22:57:14
200 POST gemini-3-flash /v1/messages?beta=true
I: 194
O: 19
3138ms 22:57:14
400 POST claude-sonnet-4-5 /v1/messages?beta=true 2757ms 22:57:14
404 POST claude-sonnet-4-5 /v1/messages/v1/messages?beta=true 0ms 22:56:38
404 POST claude-sonnet-4-5 /v1/messages/v1/messages?beta=true 1ms 22:56:38
404 POST gemini-3-flash /v1/messages/v1/messages?beta=true 0ms 22:56:38
404 POST gemini-3-flash /v1/messages/v1/messages?beta=true 0ms 22:56:38
400
POST
/v1/messages?beta=true
请求时间
2026/1/5 22:59:23
耗时
305ms
TOKEN 消耗 (输入/输出)
In: 0
Out: 0
使用模型
claude-sonnet-4-5
请求报文 (REQUEST)
{
"model": "claude-sonnet-4-5",
"messages": [
{
"role": "user",
"content": [
{
{
"name": "mcp__plugin_claude-mem_mcp-search____IMPORTANT",
"description": "3-LAYER WORKFLOW (ALWAYS FOLLOW):\n1. search(query) → Get index with IDs (~50-100 tokens/result)\n2. timeline(anchor=ID) → Get context around interesting results\n3. get_observations([IDs]) → Fetch full details ONLY for filtered IDs\nNEVER fetch full details without filtering first.
10x token savings.",
"input_schema": {
"type": "object",
"properties": {}
}
},
{
"name": "mcp__plugin_claude-mem_mcp-search__search",
"description": "Step 1: Search memory.
Returns index with IDs.
Params: query, limit, project, type, obs_type, dateStart, dateEnd, offset, orderBy",
"input_schema": {
"type": "object",
"properties": {},
"additionalProperties": true
}
},
{
"name": "mcp__plugin_claude-mem_mcp-search__timeline",
"description": "Step 2: Get context around results.
Params: anchor (observation ID) OR query (finds anchor automatically), depth_before, depth_after, project",
"input_schema": {
"type": "object",
"properties": {},
"additionalProperties": true
}
},
{
"name": "mcp__plugin_claude-mem_mcp-search__get_observations",
"description": "Step 3: Fetch full details for filtered IDs.
Params: ids (array of observation IDs, required), orderBy, limit, project",
"input_schema": {
"type": "object",
"properties": {
"ids": {
"type": "array",
"items": {
"type": "number"
},
"description": "Array of observation IDs to fetch (required)"
}
},
"required": [
"ids"
],
"additionalProperties": true
}
},
{
"name": "mcp__Ncp__find",
"description": "Search or list MCP tools.
Call as find() - no prefix needed.
With description param: vector search tools by capability.
Without description: list all available tools.
Use pipe separator for multi-query ("gmail | slack").",
"input_schema": {
"type": "object",
"properties": {
"description": {
"type": "string",
"description": "Search query describing capability you need (e.g.
"send email", "read file").
OMIT this parameter entirely to list all tools (do not pass "list all" or empty string).
Use pipe separator for multi-query ("gmail | slack")."
},
"limit": {
"type": "number",
"description": "Max results per page (default: 5 search, 20 list)"
},
"page": {
"type": "number",
"description": "Page number (default: 1)"
},
"confidence_threshold": {
"type": "number",
"description": "Min confidence 0.0-1.0 (default: 0.35).
Lower=more results, higher=precise."
},
"depth": {
"type": "number",
"description": "Detail level: 0=names, 1=+descriptions, 2=+parameters (default: 2)",
"enum": [
0,
1,
2
]
}
}
}
},
{
"name": "mcp__Ncp__code",
"description": "Execute TypeScript with MCPs as namespaces (e.g., github.get_repo()).
Use ncp.find() for discovery.
Console captured.",
"input_schema": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "TypeScript code.
MCPs available as namespaces.
Example: await gmail.send_email({to, subject, body})"
},
"timeout": {
"type": "number",
"description": "Timeout in ms (default: 30000, max: 300000)"
}
},
"required": [
"code"
]
}
},
{
"name": "ListMcpResourcesTool",
"description": "\nList available resources from configured MCP servers.\nEach returned resource will include all standard MCP resource fields plus a 'server' field \nindicating which server the resource belongs to.\n\nParameters:\n- server (optional): The name of a specific MCP server to get resources from.
If not provided,\n resources from all servers will be returned.\n",
"input_schema": {
"type": "object",
"properties": {
"server": {
"type": "string",
"description": "Optional server name to filter resources by"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "ReadMcpResourceTool",
"description": "\nReads a specific resource from an MCP server, identified by server name and resource URI.\n\nParameters:\n- server (required): The name of the MCP server from which to read the resource\n- uri (required): The URI of the resource to read\n",
"input_schema": {
"type": "object",
"properties": {
"server": {
"type": "string",
"description": "The MCP server name"
},
"uri": {
"type": "string",
"description": "The resource URI to read"
}
},
"required": [
"server",
"uri"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__ui_to_artifact",
"description": "Convert UI screenshots into various artifacts: code, prompts, design specifications, or descriptions.\n\nUse this tool ONLY when the user wants to:\n- Generate frontend code from UI design (output_type='code')\n- Create AI prompts for UI generation (output_type='prompt')\n- Extract design specifications (output_type='spec')\n- Get natural language description of the UI (output_type='description')\n\nDo NOT use for: screenshots containing text/code to extract, error messages, diagrams, or data visualizations.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"output_type": {
"type": "string",
"enum": [
"code",
"prompt",
"spec",
"description"
],
"description": "Type of output to generate.
Options: 'code' (generate frontend code), 'prompt' (generate AI prompt for recreating this UI), 'spec' (generate design specification document), 'description' (natural language description of the UI)."
},
"prompt": {
"type": "string",
"description": "Detailed instructions describing what to generate from this UI image.
Should clearly state the desired output and any specific requirements."
}
},
"required": [
"image_source",
"output_type",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__extract_text_from_screenshot",
"description": "Extract and recognize text from screenshots using advanced OCR capabilities.\n\nUse this tool ONLY when the user has a screenshot containing text and wants to extract it.\nThis tool specializes in OCR for code, terminal output, documentation, and general text extraction.\n\nDo NOT use for: UI design conversion, error diagnosis, or diagram understanding.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "Instructions for text extraction.
Specify what type of text to extract and any formatting requirements."
},
"programming_language": {
"type": "string",
"description": "Optional: specify the programming language if the screenshot contains code (e.g., 'python', 'javascript', 'java').
Leave empty for auto-detection or non-code text."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__diagnose_error_screenshot",
"description": "Diagnose and analyze error messages, stack traces, and exception screenshots.\n\nUse this tool ONLY when the user has an error screenshot and needs help understanding or fixing it.\nThis tool specializes in error analysis and provides actionable solutions.\n\nDo NOT use for: code extraction, UI analysis, or diagram understanding.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "Description of what you need help with regarding this error.
Include any relevant context about when it occurred."
},
"context": {
"type": "string",
"description": "Optional: additional context about when the error occurred (e.g., 'during npm install', 'when running the app', 'after deployment').
Helps with more accurate diagnosis."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__understand_technical_diagram",
"description": "Analyze and explain technical diagrams including architecture diagrams, flowcharts, UML, ER diagrams, and system design diagrams.\n\nUse this tool ONLY when the user has a technical diagram and wants to understand its structure or components.\nThis tool specializes in interpreting visual technical documentation.\n\nDo NOT use for: UI screenshots, error messages, or data visualizations/charts.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "What you want to understand or extract from this diagram."
},
"diagram_type": {
"type": "string",
"description": "Optional: specify the diagram type if known (e.g., 'architecture', 'flowchart', 'uml', 'er-diagram', 'sequence').
Leave empty for auto-detection."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__analyze_data_visualization",
"description": "Analyze data visualizations, charts, graphs, and dashboards to extract insights and trends.\n\nUse this tool ONLY when the user has a data visualization image and wants to understand the data patterns or metrics.\nThis tool specializes in interpreting visual data representations.\n\nDo NOT use for: UI mockups, error messages, or technical architecture diagrams.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "What insights or information you want to extract from this visualization."
},
"analysis_focus": {
"type": "string",
"description": "Optional: specify what to focus on (e.g., 'trends', 'anomalies', 'comparisons', 'performance metrics').
Leave empty for comprehensive analysis."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__ui_diff_check",
"description": "Compare two UI screenshots to identify visual differences and implementation discrepancies.\n\nUse this tool ONLY when the user wants to compare an expected/reference UI with an actual implementation.\nThis tool is specialized for UI quality assurance and design-to-implementation verification.\n\nDo NOT use for: general image comparison, error diagnosis, or analyzing single UIs.",
"input_schema": {
"type": "object",
"properties": {
"expected_image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"actual_image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "Instructions for the comparison.
Specify what aspects to focus on or what level of detail is needed."
}
},
"required": [
"expected_image_source",
"actual_image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__analyze_image",
"description": "General-purpose image analysis for scenarios not covered by specialized tools.\n\nUse this tool as a FALLBACK when none of the other specialized tools (ui_to_artifact, extract_text_from_screenshot,\ndiagnose_error_screenshot, understand_technical_diagram, analyze_data_visualization, ui_diff_check) fit the user's need.\n\nThis tool provides flexible image understanding for any visual content.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "Detailed description of what you want to analyze, extract, or understand from the image.
Be specific about your requirements."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__analyze_video",
"description": "Analyze video content using advanced AI vision models.\n\nUse this tool when the user wants to:\n- Understand what happens in a video\n- Extract key moments or actions from video\n- Analyze video content, scenes, or sequences\n- Get descriptions of video footage\n- Identify objects, people, or activities in video\n\nSupports both local files and remote URL.
Maximum file size: 8MB.
Supports MP4, MOV, M4V formats.",
"input_schema": {
"type": "object",
"properties": {
"video_source": {
"type": "string",
"description": "Local file path or remote URL to the video (supports MP4, MOV, M4V)"
},
"prompt": {
"type": "string",
"description": "Detailed text prompt describing what to analyze, extract, or understand from the video"
}
},
"required": [
"video_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
],
"metadata": {
"user_id": "user_d6b6459ffe853fa1da6907353ee940124a6a9bd7fa071b0fd9421af648cf05e7_account__session_ab777f87-8699-4269-bc6f-5c4e39bf4436"
},
"max_tokens": 21333,
"thinking": {
"budget_tokens": 21332,
"type": "enabled"
},
"temperature": 1
}
响应报文 (RESPONSE)
{
"error": {
"code": 400,
"message": "Invalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[0]' (TYPE_STRING), 0\nInvalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[1]' (TYPE_STRING), 1\nInvalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[2]' (TYPE_STRING), 2",
"status": "INVALID_ARGUMENT",
"details": [
{
"@type": "type.googleapis.com/google.rpc.BadRequest",
"fieldViolations": [
{
"field": "request.tools[0].function_declarations[22].parameters.properties[1].value.enum[0]",
"description": "Invalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[0]' (TYPE_STRING), 0"
},
{
"field": "request.tools[0].function_declarations[22].parameters.properties[1].value.enum[1]",
"description": "Invalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[1]' (TYPE_STRING), 1"
},
{
"field": "request.tools[0].function_declarations[22].parameters.properties[1].value.enum[2]",
"description": "Invalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[2]' (TYPE_STRING), 2"
}
]
}
]
}
}
Expected behavior
A clear and concise description of what you expected to happen.
Screenshots
If applicable, add screenshots to help explain your problem.
OS Type
Additional context
在启用ncp这个mcp之后，使用antigravity得api会报错
使用这个ncp后用codex、claude接glm4.7等可以正常使用
Antigravity Tools
仪表盘
账号管理
API 反代
设置
中
API 监控看板
实时请求日志与分析
30 REQS30 REQS
22 OK22 OK
8 ERR8 ERR
快速过滤:快速过滤:
全部全部
仅错误仅错误
聊天聊天
GeminiGemini
ClaudeClaude
绘图绘图
状态 方法 模型 路径 Token 消耗 耗时 时间
状态 方法 模型 路径 Token 消耗 耗时 时间
200 POST gemini-3-flash /v1/messages?beta=true
200 POST gemini-3-flash /v1/messages?beta=true
I: 650I: 650
O: 22O: 22
904ms 22:59:23904ms 22:59:23
400 POST claude-sonnet-4-5 /v1/messages?beta=true 305ms 22:59:23
400 POST claude-sonnet-4-5 /v1/messages?beta=true 305ms 22:59:23
400 POST claude-sonnet-4-5 /v1/messages?beta=true 469ms 22:59:22
400 POST claude-sonnet-4-5 /v1/messages?beta=true 469ms 22:59:22
200 POST gemini-3-flash /v1/messages?beta=true
200 POST gemini-3-flash /v1/messages?beta=true
I: 465I: 465
O: 20O: 20
8893ms 22:58:528893ms 22:58:52
200 POST gemini-3-flash /v1/messages?beta=true
200 POST gemini-3-flash /v1/messages?beta=true
I: 4.3kI: 4.3k
O: 106O: 106
3665ms 22:58:473665ms 22:58:47
200 POST claude-sonnet-4-5 /v1/messages?beta=true
200 POST claude-sonnet-4-5 /v1/messages?beta=true
I: 5.9kI: 5.9k
O: 158O: 158
3017ms 22:58:463017ms 22:58:46
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 1ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 1ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST claude-sonnet-4-5 /v1/messages/count_tokens?beta=true 0ms 22:57:20
200 POST gemini-3-flash /v1/messages?beta=true
I: 6k
O: 138
5780ms 22:57:16
200 POST claude-sonnet-4-5 /v1/messages?beta=true
I: 7.8k
O: 107
4908ms 22:57:15
400 POST claude-sonnet-4-5 /v1/messages?beta=true 377ms 22:57:14
200 POST gemini-3-flash /v1/messages?beta=true
I: 194
O: 19
3138ms 22:57:14
400 POST claude-sonnet-4-5 /v1/messages?beta=true 2757ms 22:57:14
404 POST claude-sonnet-4-5 /v1/messages/v1/messages?beta=true 0ms 22:56:38
404 POST claude-sonnet-4-5 /v1/messages/v1/messages?beta=true 1ms 22:56:38
404 POST gemini-3-flash /v1/messages/v1/messages?beta=true 0ms 22:56:38
404 POST gemini-3-flash /v1/messages/v1/messages?beta=true 0ms 22:56:38
400
POST
/v1/messages?beta=true
请求时间
2026/1/5 22:59:23
耗时
305ms
TOKEN 消耗 (输入/输出)
In: 0
Out: 0
使用模型
claude-sonnet-4-5
请求报文 (REQUEST)
{
"model": "claude-sonnet-4-5",
"messages": [
{
"role": "user",
"content": [
{
{
"name": "mcp__plugin_claude-mem_mcp-search____IMPORTANT",
"description": "3-LAYER WORKFLOW (ALWAYS FOLLOW):\n1. search(query) → Get index with IDs (~50-100 tokens/result)\n2. timeline(anchor=ID) → Get context around interesting results\n3. get_observations([IDs]) → Fetch full details ONLY for filtered IDs\nNEVER fetch full details without filtering first.
10x token savings.",
"input_schema": {
"type": "object",
"properties": {}
}
},
{
"name": "mcp__plugin_claude-mem_mcp-search__search",
"description": "Step 1: Search memory.
Returns index with IDs.
Params: query, limit, project, type, obs_type, dateStart, dateEnd, offset, orderBy",
"input_schema": {
"type": "object",
"properties": {},
"additionalProperties": true
}
},
{
"name": "mcp__plugin_claude-mem_mcp-search__timeline",
"description": "Step 2: Get context around results.
Params: anchor (observation ID) OR query (finds anchor automatically), depth_before, depth_after, project",
"input_schema": {
"type": "object",
"properties": {},
"additionalProperties": true
}
},
{
"name": "mcp__plugin_claude-mem_mcp-search__get_observations",
"description": "Step 3: Fetch full details for filtered IDs.
Params: ids (array of observation IDs, required), orderBy, limit, project",
"input_schema": {
"type": "object",
"properties": {
"ids": {
"type": "array",
"items": {
"type": "number"
},
"description": "Array of observation IDs to fetch (required)"
}
},
"required": [
"ids"
],
"additionalProperties": true
}
},
{
"name": "mcp__Ncp__find",
"description": "Search or list MCP tools.
Call as find() - no prefix needed.
With description param: vector search tools by capability.
Without description: list all available tools.
Use pipe separator for multi-query ("gmail | slack").",
"input_schema": {
"type": "object",
"properties": {
"description": {
"type": "string",
"description": "Search query describing capability you need (e.g.
"send email", "read file").
OMIT this parameter entirely to list all tools (do not pass "list all" or empty string).
Use pipe separator for multi-query ("gmail | slack")."
},
"limit": {
"type": "number",
"description": "Max results per page (default: 5 search, 20 list)"
},
"page": {
"type": "number",
"description": "Page number (default: 1)"
},
"confidence_threshold": {
"type": "number",
"description": "Min confidence 0.0-1.0 (default: 0.35).
Lower=more results, higher=precise."
},
"depth": {
"type": "number",
"description": "Detail level: 0=names, 1=+descriptions, 2=+parameters (default: 2)",
"enum": [
0,
1,
2
]
}
}
}
},
{
"name": "mcp__Ncp__code",
"description": "Execute TypeScript with MCPs as namespaces (e.g., github.get_repo()).
Use ncp.find() for discovery.
Console captured.",
"input_schema": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "TypeScript code.
MCPs available as namespaces.
Example: await gmail.send_email({to, subject, body})"
},
"timeout": {
"type": "number",
"description": "Timeout in ms (default: 30000, max: 300000)"
}
},
"required": [
"code"
]
}
},
{
"name": "ListMcpResourcesTool",
"description": "\nList available resources from configured MCP servers.\nEach returned resource will include all standard MCP resource fields plus a 'server' field \nindicating which server the resource belongs to.\n\nParameters:\n- server (optional): The name of a specific MCP server to get resources from.
If not provided,\n resources from all servers will be returned.\n",
"input_schema": {
"type": "object",
"properties": {
"server": {
"type": "string",
"description": "Optional server name to filter resources by"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "ReadMcpResourceTool",
"description": "\nReads a specific resource from an MCP server, identified by server name and resource URI.\n\nParameters:\n- server (required): The name of the MCP server from which to read the resource\n- uri (required): The URI of the resource to read\n",
"input_schema": {
"type": "object",
"properties": {
"server": {
"type": "string",
"description": "The MCP server name"
},
"uri": {
"type": "string",
"description": "The resource URI to read"
}
},
"required": [
"server",
"uri"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__ui_to_artifact",
"description": "Convert UI screenshots into various artifacts: code, prompts, design specifications, or descriptions.\n\nUse this tool ONLY when the user wants to:\n- Generate frontend code from UI design (output_type='code')\n- Create AI prompts for UI generation (output_type='prompt')\n- Extract design specifications (output_type='spec')\n- Get natural language description of the UI (output_type='description')\n\nDo NOT use for: screenshots containing text/code to extract, error messages, diagrams, or data visualizations.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"output_type": {
"type": "string",
"enum": [
"code",
"prompt",
"spec",
"description"
],
"description": "Type of output to generate.
Options: 'code' (generate frontend code), 'prompt' (generate AI prompt for recreating this UI), 'spec' (generate design specification document), 'description' (natural language description of the UI)."
},
"prompt": {
"type": "string",
"description": "Detailed instructions describing what to generate from this UI image.
Should clearly state the desired output and any specific requirements."
}
},
"required": [
"image_source",
"output_type",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__extract_text_from_screenshot",
"description": "Extract and recognize text from screenshots using advanced OCR capabilities.\n\nUse this tool ONLY when the user has a screenshot containing text and wants to extract it.\nThis tool specializes in OCR for code, terminal output, documentation, and general text extraction.\n\nDo NOT use for: UI design conversion, error diagnosis, or diagram understanding.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "Instructions for text extraction.
Specify what type of text to extract and any formatting requirements."
},
"programming_language": {
"type": "string",
"description": "Optional: specify the programming language if the screenshot contains code (e.g., 'python', 'javascript', 'java').
Leave empty for auto-detection or non-code text."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__diagnose_error_screenshot",
"description": "Diagnose and analyze error messages, stack traces, and exception screenshots.\n\nUse this tool ONLY when the user has an error screenshot and needs help understanding or fixing it.\nThis tool specializes in error analysis and provides actionable solutions.\n\nDo NOT use for: code extraction, UI analysis, or diagram understanding.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "Description of what you need help with regarding this error.
Include any relevant context about when it occurred."
},
"context": {
"type": "string",
"description": "Optional: additional context about when the error occurred (e.g., 'during npm install', 'when running the app', 'after deployment').
Helps with more accurate diagnosis."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__understand_technical_diagram",
"description": "Analyze and explain technical diagrams including architecture diagrams, flowcharts, UML, ER diagrams, and system design diagrams.\n\nUse this tool ONLY when the user has a technical diagram and wants to understand its structure or components.\nThis tool specializes in interpreting visual technical documentation.\n\nDo NOT use for: UI screenshots, error messages, or data visualizations/charts.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "What you want to understand or extract from this diagram."
},
"diagram_type": {
"type": "string",
"description": "Optional: specify the diagram type if known (e.g., 'architecture', 'flowchart', 'uml', 'er-diagram', 'sequence').
Leave empty for auto-detection."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__analyze_data_visualization",
"description": "Analyze data visualizations, charts, graphs, and dashboards to extract insights and trends.\n\nUse this tool ONLY when the user has a data visualization image and wants to understand the data patterns or metrics.\nThis tool specializes in interpreting visual data representations.\n\nDo NOT use for: UI mockups, error messages, or technical architecture diagrams.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "What insights or information you want to extract from this visualization."
},
"analysis_focus": {
"type": "string",
"description": "Optional: specify what to focus on (e.g., 'trends', 'anomalies', 'comparisons', 'performance metrics').
Leave empty for comprehensive analysis."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__ui_diff_check",
"description": "Compare two UI screenshots to identify visual differences and implementation discrepancies.\n\nUse this tool ONLY when the user wants to compare an expected/reference UI with an actual implementation.\nThis tool is specialized for UI quality assurance and design-to-implementation verification.\n\nDo NOT use for: general image comparison, error diagnosis, or analyzing single UIs.",
"input_schema": {
"type": "object",
"properties": {
"expected_image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"actual_image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "Instructions for the comparison.
Specify what aspects to focus on or what level of detail is needed."
}
},
"required": [
"expected_image_source",
"actual_image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__analyze_image",
"description": "General-purpose image analysis for scenarios not covered by specialized tools.\n\nUse this tool as a FALLBACK when none of the other specialized tools (ui_to_artifact, extract_text_from_screenshot,\ndiagnose_error_screenshot, understand_technical_diagram, analyze_data_visualization, ui_diff_check) fit the user's need.\n\nThis tool provides flexible image understanding for any visual content.",
"input_schema": {
"type": "object",
"properties": {
"image_source": {
"type": "string",
"description": "Local file path or remote URL to the image"
},
"prompt": {
"type": "string",
"description": "Detailed description of what you want to analyze, extract, or understand from the image.
Be specific about your requirements."
}
},
"required": [
"image_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
},
{
"name": "mcp__zai-mcp-server__analyze_video",
"description": "Analyze video content using advanced AI vision models.\n\nUse this tool when the user wants to:\n- Understand what happens in a video\n- Extract key moments or actions from video\n- Analyze video content, scenes, or sequences\n- Get descriptions of video footage\n- Identify objects, people, or activities in video\n\nSupports both local files and remote URL.
Maximum file size: 8MB.
Supports MP4, MOV, M4V formats.",
"input_schema": {
"type": "object",
"properties": {
"video_source": {
"type": "string",
"description": "Local file path or remote URL to the video (supports MP4, MOV, M4V)"
},
"prompt": {
"type": "string",
"description": "Detailed text prompt describing what to analyze, extract, or understand from the video"
}
},
"required": [
"video_source",
"prompt"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
],
"metadata": {
"user_id": "user_d6b6459ffe853fa1da6907353ee940124a6a9bd7fa071b0fd9421af648cf05e7_account__session_ab777f87-8699-4269-bc6f-5c4e39bf4436"
},
"max_tokens": 21333,
"thinking": {
"budget_tokens": 21332,
"type": "enabled"
},
"temperature": 1
}
响应报文 (RESPONSE)
{
"error": {
"code": 400,
"message": "Invalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[0]' (TYPE_STRING), 0\nInvalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[1]' (TYPE_STRING), 1\nInvalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[2]' (TYPE_STRING), 2",
"status": "INVALID_ARGUMENT",
"details": [
{
"@type": "type.googleapis.com/google.rpc.BadRequest",
"fieldViolations": [
{
"field": "request.tools[0].function_declarations[22].parameters.properties[1].value.enum[0]",
"description": "Invalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[0]' (TYPE_STRING), 0"
},
{
"field": "request.tools[0].function_declarations[22].parameters.properties[1].value.enum[1]",
"description": "Invalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[1]' (TYPE_STRING), 1"
},
{
"field": "request.tools[0].function_declarations[22].parameters.properties[1].value.enum[2]",
"description": "Invalid value at 'request.tools[0].function_declarations[22].parameters.properties[1].value.enum[2]' (TYPE_STRING), 2"
}
]
}
]
}
}