codebase-memory-mcp MCP server

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

What codebase-memory-mcp does

Summarised from the project README; check the repository for the latest details.

Features

• Architecture Decision Records: `manageadr` persists architectural decisions across sessions
• Louvain community detection: Discovers functional modules by clustering call edges
• Git diff impact mapping: `detectchanges` maps uncommitted changes to affected symbols with risk classification
• Call graph: Resolves function calls across files and packages (import-aware, type-inferred)
• Dead code candidates: find functions with no indexed callers, excluding entry points. Check dynamic dispatch, coverage gaps, and framework conventions before removing code.
• Cypher-like queries: `MATCH (f:Function)-[:CALLS]->(g) WHERE f.name = 'main' RETURN g.name`

Tools exposed (19)

• Indexing
• index_repository – Index a repository into the graph. Auto-sync keeps it fresh only while it is the project of an open MCP session; repos indexed from the CLI
• list_projects – List all indexed projects with node/edge counts.
• delete_project – Remove a project and all its graph data.
• index_status – Check indexing status of a project.
• check_index_coverage – Check whether exact paths or a scope are indexed and fresh. A clean result means no recorded gap, not proof of completeness.
• Querying
• search_graph – Structural, BM25, and semantic search. Page structural rows with `offset`/`limit` and ranked semantic rows independently with `semanticoffse
• trace_path – Trace callers, callees, data flow, or cross-service paths (alias: `tracecallpath`). Depth 1 to 15; tests are excluded by default. `mode`: `c
• detect_changes – Map git diff to affected symbols + blast radius with risk classification.
• query_graph – Execute Cypher-like graph queries (read-only).
• get_graph_schema – Node/edge counts, relationship patterns, property definitions per label. Run this first.
• compare_graphs – Compare two indexed snapshots: node/edge additions and removals between a base and a target.
• get_code_snippet – Read source code for a function by qualified name.
• get_file_outline – Declaration outline of one repository-relative file in source order, with optional label filter and paging.
• get_architecture – Codebase overview: languages, packages, routes, hotspots, clusters, ADR.
• search_code – Grep-like text search within indexed project files.
• manage_adr – CRUD for Architecture Decision Records (`get` reads, `update` replaces the whole document, `setsections` rewrites only the named sections an
• ingest_traces – Store observed call paths or caller/callee pairs under a run label. Both endpoints must resolve to indexed symbols; unresolved names are rep

How to install codebase-memory-mcp

Featured in: Best MCP servers for Claude Desktop · Best MCP servers for Cursor · Best MCP servers for coding · Best MCP servers for long-term memory · Best MCP servers for Claude Code

Listed on Socketlist – add this badge to your README:

Badge markdown[](https://socketlist.pages.dev/s/deusdata-codebase-memory-mcp/)

Maintain this project? Get it featured for free during launch →

Compare with nightingale →

Related Databases MCP servers