Codebase Memory MCP Builds Knowledge Graphs to Help AI Coding Agents Navigate Projects
Codebase Memory MCP is an open-source MCP server designed to help AI coding agents like Claude Code, Codex, and Cursor understand large frontend codebases more efficiently. It parses source code using Tree-sitter and indexes relationships between components, hooks, stores, services, and APIs into a structured knowledge graph. Instead of scanning multiple files from scratch for every task, an agent can query the graph to quickly identify relevant code paths and dependencies. The tool acts as an intermediary layer between the coding agent and the codebase, exposing structured results via the Model Context Protocol interface. The project is available on GitHub under the repository DeusData/codebase-memory-mcp.
This is an AI-generated summary. ShortSingh links to the original source for the complete article.
Discussion (0)
Log in to join the discussion and vote.
Log in