High-performance MCP server that indexes codebases into a persistent knowledge graph for AI coding agents.
codebase-memory-mcp is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view DeusData/codebase-memory-mcp --webOpen the official README and confirm the supported install method.
Add the server entry to your MCP client config.
Restart your agent and verify that the server tools appear.
Repository setup guidance
Strong trust signals; still review the README and permissions before production use.
Last commit was about 50 days ago.
39249 GitHub stars indicate community interest.
459 open issues signal maintenance load.
MIT license detected.
5 security/trust notes recorded.
Setup difficulty is 3/5.
Official MCP reference servers from Anthropic. Includes servers for filesystem, GitHub, Postgres, Slack, and more.
A secure MCP server for AI applications to interact with MySQL databases.
Up-to-date code documentation for LLMs and AI code editors, eliminating outdated or hallucinated API references.
Zero-dependency, token-efficient MCP server for querying multiple databases via a single interface.
This tool helps AI coding assistants understand your codebase quickly. It scans your code and builds a searchable map of functions, classes, and connections. This lets the AI answer questions about your code without reading every file, saving time and tokens.
codebase-memory-mcp is a Model Context Protocol (MCP) server designed to give AI coding agents instant, deep understanding of codebases. It uses tree-sitter to parse 158 languages and a hybrid LSP for semantic type resolution in 10 languages, building a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. The server indexes an average repository in milliseconds and the Linux kernel (28M LOC) in 3 minutes, with sub-millisecond query times. It provides 15 MCP tools for structural queries, reducing token usage by up to 99% compared to file-by-file exploration. The tool is a single static binary with zero dependencies, runs fully locally, and supports macOS, Linux, and Windows. It integrates with 43 agent surfaces including Claude Code, Codex, Cursor, and Windsurf. The project is backed by research (arXiv:2603.27277) showing 83% answer quality and 10x fewer tokens. Security is a priority: all processing is local, and releases are scanned with VirusTotal and SLSA 3 compliance.
39,249
Stars
3,143
Forks
459
Issues
MIT
License
High-performance MCP server that indexes codebases into a persistent knowledge graph for AI coding agents.
AI coding agent power users (Claude Code, Codex, Cursor)
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
The tool reads your codebase and writes to agent configuration files; audit before running. All processing is local
Similar or complementary options to evaluate include MCP Server Collection, mysql_mcp_server, context7.
Aug 20, 2026