WIP: add tool outputSchema and DataContent type to support structured content #685
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ly need an opt out for conversion to automatic conversion to DataContent
9 tasks
davemssavage
commented
May 12, 2025
| self.fn, | ||
| self.is_async, | ||
| arguments, | ||
| {self.context_kwarg: context} | ||
| if self.context_kwarg is not None | ||
| else None, | ||
| ) | ||
| if self.output and self.output.get("type") == "object": |
There was a problem hiding this comment.
This logic is debatable it introduces a breaking change, potential to make this opt-in or opt-out by adding a flag to the @mcp.tool() annotation something like @mcp.tool(enable_data_content=True)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Enable tool to return data content and schema.
Motivation and Context
As per discussion in modelcontextprotocol/modelcontextprotocol#356 there are use cases where being able to know the schema of a tool is useful prior to calling it. This patch is an experiment to enable me to test this behaviour, it is far from finished and depends on the above RFC being accepted before it is merged, however opening a draft pull request for comment
How Has This Been Tested?
Local unit testing only so far
Breaking Changes
At the moment yes, this patch results in DataContent items being returned whenever a complex object is returned from a tool, this may result in breaking changes in clients. Some thought needs to go into how best to tackle this.
Types of changes
Checklist
Additional context
Updates to documentation will be required if this patch is approved