CodeRAG
Parses TypeScript, JavaScript, Java, and Python codebases into a Neo4J graph database to extract code entities, relationships, and
This MCP server provides comprehensive code analysis and graph-based exploration of software projects by parsing TypeScript, JavaScript, Java, and Python codebases into a Neo4J graph database. Built by Jonathan Crabtree using TypeScript with the MCP SDK and Neo4J driver, it extracts code entities (classes, methods, functions, interfaces) and their relationships (inheritance, method calls, dependencies) while capturing rich metadata including annotations, decorators, and framework usage patterns. The implementation offers both STDIO and HTTP/SSE transport modes, includes 18 analysis tools for calculating software quality metrics (CK metrics suite, package coupling, architectural issues), and provides guided prompts for dependency analysis and inheritance exploration, making it valuable for understanding large codebases, identifying architectural problems, refactoring legacy systems, and performing code quality assessments through AI-powered graph traversal and relationship analysis.
Source
Repository: https://github.com/jonnoc/coderag
Maintain CodeRAG?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[CodeRAG on getagentictools](https://getagentictools.com/mcp/jonnoc-coderag?ref=badge) Related mcp
Lenses Explore, transform, and join data in Kafka topics across multiple clusters
PostgreSQL Advanced Provides full read-write PostgreSQL database access with transaction management, connection pooling, and safety features that requ
Cursor DB Explorer Provides access to Cursor IDE's SQLite databases for exploring project data, chat history, and composer information through an API
Oracle Database Provides secure, read-only access to Oracle databases through Python's oracledb library, enabling database schema exploration and
Prometheus Integrates with Prometheus monitoring systems to provide direct access to time-series metrics through specialized tools for discov
MemGPT Implements a multi-provider memory system for LLMs, enabling conversation history management and seamless model switching across O