Minimal MCP server for AI agent integration #2298
Open
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Outdated suggestions cannot be applied.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.
Use Fizzy from your favorite LLM. Even use Fizzy as a coordination bus for your agents, workflows, and skills. Fluent, fast, no bloat.
This is a simple, purposefully bare-bones trial-balloon implementation with no new abstractions or modeling. (Rails' take on MCP should elegantly satisfy what we're after here, but this isn't the PR for it.)
Model Context Protocol 2025-06-18 with streamable HTTP. Resource responses are concise to limit token bloat and keep context window creep under control.
Endpoints:
Tools (create_board, create_card, update_card, move_card) for workspace management. Resources for reading accounts, boards, and cards via fizzy:// URI scheme.
Builds on OAuth 2.1 support for seamless authentication: #2296