Adds basic MCP integration #549
Draft
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
|
|
||
|
|
||
| app = FastAPI(lifespan=lifespan) | ||
| app.mount("/", mcp_app.sse_app()) |
Collaborator
There was a problem hiding this comment.
sse is deprecated on MCP, FYI
Contributor
Author
There was a problem hiding this comment.
yeah, I know. It was working for a bit (added it to the lifespan with the async context manager), but then something went sideways, and it consistently stopped working. I stopped debugging. The vibes I'm getting are that SSE is deprecated, but streaming is not yet very stable 😭
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Outdated suggestions cannot be applied.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.
This would be better to mount to each deployment at a sub-path, but this was just a quick hack as a demo. This shouldn't be merged, just putting it here as a reference.
It includes an example mcp server that acts as a knowledge base that can scrape data from the web, to act as a documentation helper.
In general, I found the event formatting and the meta data (descriptions) to be the more complex part. If we pursue something like this, it might be nice to add some mechanism to be able to have a format Event outputs to one more suitable for a model's consumption, rather than just dumping out the json.