WS-C: CogniFold MCP server + integration docs - #14
Merged
Merged
Conversation
- src/cognifold/mcp/: FastMCP stdio server wrapping existing Pipeline / MemoryQueryAgent / persistence (4 tools: remember, query, graph_stats, list_intents). Optional `mcp` SDK import is guarded with an install hint; logging retargeted to stderr so stdio JSON-RPC stays clean. - pyproject: `mcp` extra + `cognifold-mcp` script. Bumped requires-python to >=3.10 (mcp>=1.0 needs it; project already targets 3.11+) and regenerated uv.lock so `uv` resolution works repo-wide. - docs/INTEGRATIONS.md: Claude Desktop / Claude Code / Cursor config + roadmap. Algorithm untouched — MCP wraps existing logic. pyright(strict) clean. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018Cafgnpw3v7U3f2Lt1ASxs
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Exposes CogniFold as an MCP server so it plugs into Claude Code / Claude Desktop / Cursor. Wraps existing logic — algorithm untouched.
src/cognifold/mcp/: FastMCP stdio server, 4 tools (remember/query/graph_stats/list_intents) wrappingPipeline/MemoryQueryAgent/graph.persistence. OptionalmcpSDK import guarded with install hint; logging retargeted to stderr to keep stdio JSON-RPC clean.pyproject.toml:mcpextra +cognifold-mcpscript. Bumpedrequires-pythonto>=3.10(mcp>=1.0 requires it; project already targets 3.11+) and regenerateduv.locksouvresolves repo-wide.docs/INTEGRATIONS.md: Claude Desktop / Claude Code / Cursor config + remember→query example + roadmap.pyright(strict) clean on mcp/; import + live round-trip verified (graph persists across calls).
🤖 Generated with Claude Code
https://claude.ai/code/session_018Cafgnpw3v7U3f2Lt1ASxs