The code-graph-rag-mcp server enables AI agents to analyze codebases using LiteRAG for graph-based retrieval. It provides tools for parsing code into graphs, querying code relationships, and retrieving relevant code snippets. The server connects to GitHub repositories and exposes APIs for code graph construction, traversal, and semantic search. Developers use it to build AI-powered code analysis tools, automate code reviews, and enhance developer productivity.
The code-graph-rag-mcp server enables AI agents to analyze codebases using LiteRAG for graph-based retrieval. It provides tools for parsing code into graphs, querying code relationships, and retrieving relevant code snippets. The server connects to GitHub repositories and exposes APIs for code graph construction, traversal, and semantic search. Developers use it to build AI-powered code analysis tools, automate code reviews, and enhance developer productivity.
npx -y @er77/code-graph-rag-mcpAdd this configuration to your claude_desktop_config.json:
{
"mcpServers": {
"er77-code-graph-rag-mcp-npm": {
"command": "npx",
"args": [
"-y",
"npx -y @er77/code-graph-rag-mcp"
]
}
}
}Restart Claude Desktop, then ask:
"What tools do you have available from code-graph-rag-mcp?"
No configuration required. This server works out of the box.
"What resources are available in code-graph-rag-mcp?"
Claude will query available resources and return a list of what you can access.
"Show me details about [specific item] in code-graph-rag-mcp"
Claude will fetch and display detailed information about the requested item.
"Create a new [item] in code-graph-rag-mcp with [details]"
Claude will use the appropriate tool to create the resource and confirm success.
We build custom MCP integrations for B2B companies. From simple connections to complex multi-tool setups.