Repo Graph
Structural graph map of any codebase so LLMs navigate by structure rather than guesswork.
Repo Graph builds a structural graph representation of any codebase, exposing relationships between files, modules, classes, and functions to help AI agents navigate code by structure rather than raw text. It installs via the PyPI package mcp-repo-graph and integrates with Claude Code, Cursor, and other MCP clients for code exploration and analysis tasks.
Source
Repository: https://github.com/james-chahwan/repo-graph
Maintain Repo Graph?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/mcp/james-chahwan-repo-graph?ref=badge) Related mcp
CodeLedger Deterministic context selection and local repository memory for AI coding agents.
Agoragentic Agent OS for autonomous agents — tool wrappers, receipt-backed execution, and USDC settlement on Base.
Think Tool Provides a structured thought process management system for maintaining explicit reasoning steps, policy verification, and tool ou
LLM CLI Gateway Unified MCP gateway bridging Claude Code, Codex, and Gemini CLI interfaces.
PaddleOCR Integrates with PaddleOCR and PP-StructureV3 to extract text from images and PDFs with confidence scores and bounding boxes, plus
Netdata Real-time infrastructure monitoring with metrics, logs, alerts, and ML anomaly detection