mcp server

Codebase Memory

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

Description as published by the maintainer. Source

• version 0.11.0
• active
• memory and context

active — Most recent push to the repository was 2026-09-25. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.

What this server can do

8 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

get_architecture(path, aspects, project)

Get high-level architecture overview — packages, services, dependencies, and project structure at a glance. Includes 'clusters': Leiden community detection over the call/import graph, surfacing the de-facto modules (each with a label, member count, cohesion score, representative top_nodes, and the packages/edge_types that bind it) — use these to grasp the real architectural seams, which often cut across the folder layout. Optional path scopes analysis to nodes under that directory prefix (file_path). Required: project.

get_code_snippet(project, qualified_name, include_neighbors)

Read source code for a function/class/symbol. IMPORTANT: First call search_graph to find the exact qualified_name, then pass it here. This is a read tool, not a search tool. Accepts full qualified_name (exact match) or short function name (returns suggestions if ambiguous). Required: qualified_name, project.

get_graph_schema(project)

Get the schema of the knowledge graph (node labels, edge types) Required: project.

index_repository(mode, name, repo_path, persistence, target_projects)

Index a repository into the knowledge graph. Special mode 'cross-repo-intelligence': skip extraction, only match Routes/Channels across projects to create CROSS_HTTP_CALLS/CROSS_ASYNC_CALLS/CROSS_CHANNEL edges. Requires target_projects param. Ensure target projects have fresh indexes first. Required: repo_path.

query_graph(query, project, max_rows)

Execute a Cypher query against the knowledge graph for complex multi-hop patterns, aggregations, and cross-service analysis. The response includes 'total' (returned row count). There is a hard 100k row ceiling — for broad queries add LIMIT in the Cypher itself or use search_graph + offset/limit pagination instead. COMPLEXITY / BOTTLENECKS: every Function and Method node carries queryable complexity properties — cyclomatic (complexity), cognitive, loop_count, loop_depth (max nested-loop depth, a polynomial-degree proxy), plus interprocedural transitive_loop_depth (worst-case nested-loop degree propagated along CALLS edges) and a recursive flag. Additional hot-path signals: linear_scan_in_loop (count of find/contains/indexOf-style scans inside a loop — the hidden O(n^2) that loop_depth misses), alloc_in_loop (allocations/appends inside a loop), recursion_in_loop (a self-call inside a loop), unguarded_recursion (recursion with no conditionally-guarded base case), param_count and max_access_depth (structure smells). Find all hot-path candidates in one query, e.g. MATCH (f:Function) WHERE f.transitive_loop_depth >= 3 OR f.linear_scan_in_loop >= 1 RETURN f.qualified_name, f.transitive_loop_depth, f.linear_scan_in_loop ORDER BY f.transitive_loop_depth DESC. Required: query, project.

search_code(mode, limit, regex, context, pattern, project, path_filter, file_pattern)

Graph-augmented code search. Finds text patterns via grep, then enriches results with the knowledge graph: deduplicates matches into containing functions, ranks by structural importance (definitions first, popular functions next, tests last). Modes: compact (default, signatures only — token efficient), full (with source), files (just file paths). Use path_filter regex to scope results. TRUNCATION: enriched results are capped at limit (default 10). Response carries 'total_grep_matches' (raw grep hit count) and 'total_results' (deduplicated function count) — compare to limit to detect truncation. There is no offset parameter; to see more, raise limit or narrow the query with file_pattern / path_filter. Required: pattern, project.

search_graph(label, limit, query, offset, project, max_degree, min_degree, qn_pattern, file_pattern, name_pattern, relationship, semantic_query, include_connected, exclude_entry_points)

Search the code knowledge graph for functions, classes, routes, and variables. Use INSTEAD OF grep/glob when finding code definitions, implementations, or relationships. Three search modes: (1) query='update settings' for BM25 ranked full-text search with camelCase splitting and structural label boosting — recommended for natural-language discovery; (2) name_pattern='.*regex.*' for exact pattern matching; (3) semantic_query=[...] for vector cosine search that bridges vocabulary (finds 'publish' when you search 'send'). The three modes are independent and can be combined in a single call. PAGINATION: results are capped at limit (default 200) — broader queries are silently truncated. The response always includes 'total' (full match count before limit) and 'has_more' (true when total > offset+returned). Detect truncation with has_more, then page by re-calling with offset=offset+limit until has_more is false. Narrow first via label/file_pattern/min_degree before paginating large result sets. Required: project.

trace_path(mode, depth, project, direction, edge_types, risk_labels, function_name, include_tests, parameter_name)

Trace paths through the code graph. Modes: calls (callers/callees), data_flow (value propagation with args at each hop), cross_service (through HTTP/async Route nodes). Use INSTEAD OF grep for callers, dependencies, impact analysis, or data flow tracing. Required: function_name, project.

Last successful function declaration observed on 2026-08-13. Source: pkg:npm/codebase-memory-mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: pkg:npm/codebase-memory-mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Repository — https://github.com/DeusData/codebase-memory-mcp
• Website — https://deusdata.github.io/codebase-memory-mcp/
• npm: codebase-memory-mcp
• pypi: codebase-memory-mcp

Related, by what their authors tagged them

• io.github.cdeust/hypermnesia-mcp-viz — last commit 2026-09-29, shares gemini-cli, graph-visualization, knowledge-graph
  Read-only visualization for Cortex memory, knowledge, sessions, traces, and codebase graphs.
• io.github.cdeust/automatised-pipeline — last commit 2026-09-30, shares code-intelligence, cypher, gemini-cli
  Codebase intelligence MCP server — index any repo into a property graph; 26 tools for agents.
• Booboo — last commit 2026-08-14, shares graph-visualization, knowledge-graph
  Query your AI system's wiring, knowledge, memory, agents and crons as one rooted graph over MCP.
• Booboo — last commit 2026-08-14, shares graph-visualization, knowledge-graph
  Query your AI system's wiring, knowledge, memory, agents and crons as one rooted graph over MCP.
• io.github.lonniev/cypher-mcp — last commit 2026-09-22, shares cypher, knowledge-graph
  Monetized graph answers via named Cypher queries — Tollbooth DPYC operator
• Toon Memory — last commit 2026-08-05, shares aider, opencode, windsurf
  Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM
• ForgeCraft — last commit 2026-09-14, shares aider, windsurf
  Production engineering standards for AI coding assistants. Setup once, remove when done.
• io.github.asklokesh/loki-mode — last commit 2026-09-30, shares aider
  Autonomous spec-to-product coding-agent CLI with an MCP server exposing 36 tools over stdio.
• io.github.chernistry/bernstein — last commit 2026-09-30, shares aider
  Declarative agent orchestration for engineering teams
• Django ORM Lens — last commit 2026-09-22, shares aider
  Django ORM static analysis MCP. Models, relations, migrations, indexes, signals, N+1.

These share tags the maintainers applied themselves, such as gemini-cli, graph-visualization, knowledge-graph, code-intelligence. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

How the author describes it

Topics the maintainer set on GitHub: aider, ast, claude-code, code-analysis, code-intelligence, codex, cursor, cypher, developer-tools, gemini-cli, graph-visualization, kilocode, knowledge-graph, mcp, mcp-server, model-context-protocol, opencode, sqlite, tree-sitter, windsurf.