Code Graph RAG MCP Server

Sponsor https://accelerator.slider-ai.ru/

Advanced Multi-Language Code Analysis with Semantic Intelligence

A powerful Model Context Protocol server that creates intelligent graph representations of your codebase with comprehensive semantic analysis capabilities.

🌟 11 Languages Supported | ⚡ 5.5x Faster | 🔍 Semantic Search | 📊 26 MCP Methods

---

🚀 Quick Start

Installation

LATEST VERSION ONLY FROM GitHub Realeases

do not use npm repository any more

# Install globally
npm install -g ./er77-code-graph-rag-mcp-2.7.12.tgz
code-graph-rag-mcp --version

Claude Desktop Integration

# Quick setup (recommended)
npx @modelcontextprotocol/inspector add code-graph-rag \
  --command "npx" \
  --args "@er77/code-graph-rag-mcp /path/to/your/codebase"

or

#
  claude mcp add-json  code-graph-rag ' { 
        "command": "npx",
        "args": ["@er77/code-graph-rag-mcp", "/_work_fodler"],
  "env": {
    "MCP_TIMEOUT": "80000"
  }
      }

Manual setup: Add to Claude Desktop config → See detailed instructions

Claude Code Integration

Claude Code (the CLI, claude) enforces a hardcoded 15-second timeout on every MCP tool call. When using a hosted embedding provider (OpenAI, Gemini via OpenAI-compat, etc.), the default 50-seed cache warmup can push the first semantic_search call past this limit and return timed out after 15000ms — even though subsequent calls complete in well under a second.

Recommended setup:

claude mcp add code-graph-rag -s user \
  -e MCP_EMBEDDING_PROVIDER=openai \
  -e MCP_EMBEDDING_MODEL=gemini-embedding-001 \
  -e MCP_EMBEDDING_ENABLED=true \
  -e OPENAI_BASE_URL=https://generativelanguage.googleapis.com/v1beta/openai \
  -e OPENAI_API_KEY=YOUR_KEY \
  -e MCP_SEMANTIC_WARMUP_LIMIT=0 \
  -- code-graph-rag-mcp /path/to/your/codebase

Key flag: MCP_SEMANTIC_WARMUP_LIMIT=0 disables the cache warmup so the semantic agent initializes in milliseconds, keeping first-query latency inside Claude Code's 15s window. Subsequent queries hit the warm agent and return in

Click to expand version history (2.5.7 - 2.3.3)

v2.5.7 - Semantic analysis improvements, lowered thresholds, clone detection

v2.5.6 - Fixed DoraAgent type collision (+16% success rate)

v2.5.5 - WASM path resolution fix, get_version tool, restart script

v2.5.4 - Architecture Decision Records (ADRs)

v2.5.3 - Deprecated dependency warning suppression

v2.5.2 - Enhanced README documentation

v2.5.1 - Python magic methods, import analysis enhancements

v2.5.0 - 8 new languages (C#, Rust, C, C++, Go, Java, VBA), Research Trinity

v2.4.1 - Rust AST parsing, system architecture docs

v2.4.0 - Health check tools, AST hotspots, semantic routing

v2.3.3 - Entity extraction fix (0 → 4,467 entities)

---

⚡ System Requirements

Minimum: Node.js 24+, 2GB RAM, Dual-core CPU

Recommended: Node.js 24+, 8GB RAM, Quad-core CPU with SSD

Known Issues

• **Deprecated boolean@3.2.0 warning**: This is a transitive dependency from the optional onnxruntime-node package (used for ML embeddings). The package is deprecated but functional. The warning can be safely ignored as it doesn't affect core functionality.

---

🤝 Contributing

1. Fork the repository

2. Follow Agent Governance rules

3. Submit pull request

Contributing Guide • Issue Tracker

---

📄 License

MIT License - see LICENSE file for details.

Links: GitHub • NPM • MCP Protocol