codebase-memory-mcp
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.
codebase-memory-mcp is a high-performance code intelligence MCP server that indexes codebases into persistent knowledge graphs in milliseconds. Built as a native C executable supporting 162 languages via tree-sitter, it provides structural analysis, semantic search, call-graph tracing, and architectural insights without requiring language runtimes or API keys. The server integrates with 45+ AI coding agents including Claude Code, Cursor, Codex, and VS Code to deliver graph-based code exploration that reduces token usage by 99% compared to file-by-file search.
Key Features
Use Cases
- 01Rapidly understanding unfamiliar codebases through architectural overviews and call-graph exploration
- 02Tracing function call chains across files and packages to understand execution flow
- 03Detecting dead code by finding functions with zero callers excluding entry points
- 04Mapping git changes to impacted symbols with blast-radius analysis and risk classification
- 05Cross-repository microservice analysis with HTTP route and service dependency mapping
- 06Maintaining architectural decision records (ADR) that persist across AI agent sessions
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
codebase-memory-mcp — FAQ
What is codebase-memory-mcp?+
It's a code intelligence MCP server that builds knowledge graphs of codebases for AI agents, providing structural search, call tracing, and architectural analysis across 162 programming languages without external dependencies.
How do I install codebase-memory-mcp?+
On macOS/Linux, run the one-line installer: curl -fsSL https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.sh | bash. On Windows, download install.ps1, unblock it, and execute in PowerShell. The installer auto-configures detected AI coding agents.
Which AI clients work with this MCP server?+
It supports 45+ clients including Claude Code, Codex, Cursor, VS Code, Zed, Windsurf, Cline, Aider, Continue, GitHub Copilot, and many others with automatic configuration.
Does it require API keys or external services?+
No. It runs 100% locally as a native executable with no language runtime, hosted service, or API key requirements. All indexing and queries happen on your machine.
Is codebase-memory-mcp free to use?+
Yes, it's open-source under the MIT license and free for all use cases.
What are the prerequisites?+
None for the pre-built binaries—just download and run the installer. Building from source requires a C/C++ compiler and zlib.
How do I install codebase-memory-mcp?+
Open the source repository on GitHub and follow its README. codebase-memory-mcp is a mcp server — MCP Agents Market links you directly to the official repo.
Is codebase-memory-mcp free?+
codebase-memory-mcp is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.