kimetsu
Kimetsu ships its MCP server inside the kimetsu binary: `kimetsu mcp serve` is a local stdio server that hosts (Claude Code, Codex, Cursor, Pi, OpenClaw, Gemini CLI) launch per project, exposing ~28 kimetsu_* tools over a per-project SQLite brain. `kimetsu setup --host
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport stdio
Tools
kimetsu_brain_context— Retrieve a context bundle (returns skipped true when nothing relevant, at zero overhead)kimetsu_brain_record— Capture a lesson; runs semantic dedupkimetsu_brain_status— Brain health + memory countskimetsu_brain_insights— Effectiveness analytics over recent runskimetsu_brain_memory_add— Direct memory createkimetsu_brain_memory_list— Direct memory listkimetsu_brain_memory_top— Top memorieskimetsu_brain_memory_search— Memory searchkimetsu_brain_memory_proposals— Review pending proposalskimetsu_brain_memory_accept— Accept a pending proposalkimetsu_brain_memory_reject— Reject a pending proposalkimetsu_brain_memory_invalidate— Retire a memorykimetsu_brain_memory_blame— Per-run citation attributionkimetsu_brain_memory_conflicts— List ingest conflictskimetsu_brain_conflict_resolve— Settle an ingest conflictkimetsu_brain_prune— List (or invalidate) net-negative memorieskimetsu_brain_model_list— Inspect available embedding modelskimetsu_brain_model_set— Switch the embedding modelkimetsu_brain_reindex— Re-embed the brain after a model changekimetsu_brain_ingest_repo— Index repo files + manifestskimetsu_benchmark_context— Task-aware playbookkimetsu_benchmark_record_outcome— Outcome recording for the task-aware playbookkimetsu_bridge_*— Skill registry discovery, import, export, sync (a family of tools; individual names not enumerated on the docs page)kimetsu_skills_search— Search the cross-harness skill registrykimetsu_brain_cite— Record that a memory materially helpedkimetsu_brain_answer— Grounded, cited answer composed from memory (local model)kimetsu_brain_config_show— Show the effective configuration (named in the configuration docs)
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.