MCP ServersMCP Servers

Codegraph Mcp

Created at 2 months ago

by Jakedismo

starstarstarstarstar

# Transform any MCP-compatible LLM into a codebase expert through semantic intelligence A blazingly fast graphRAG implementation. 100% Rust for indexing and querying large codebases with natural language. Supports multiple embedding providers: modes cpu (no graph just AST parsing), onnx (blazingly fast medium quality embeddings with Qdrant/all-MiniLM-L6-v2-onnx) and Ollama (time consuming SOTA embeddings with hf.co/nomic-ai/nomic-embed-code-GGUF:Q4_K_M). I would argue this is the fastest codebase indexer on the Github atm. Includes a Rust SDK made stdio MCP server so that your agents can query the indexed codegraph with natural language and get deep insights from your codebase before starting development or making changes. Currently supports typescript, javascript, rust, go, Python and C++ codebases. 📊 Performance Benchmarking (M4 Max 128GB) Production Codebase Results (1,505 files, 2.5M lines, Python, Javascript, Typescript and Go) 🎉 INDEXING COMPLETE! 📊 Performance Summary ┌───────────────. ─┐ │ 📄 Files: 1,505 indexed │ │ 📝 Lines: 2,477,824 processed │ │ 🔧 Functions: 30,669 extracted │ │ 🏗️ Classes: 880 extracted │ │ 💾 Embeddings: 538,972 generated │ └───────────────. ─┘ Embedding Provider Performance Comparison Provider Time Quality Use Case 🧠 Ollama nomic-embed-code ~15-18h SOTA retrieval accuracy Production, smaller codebases ⚡ ONNX all-MiniLM-L6-v2 32m 22s Good general embeddings Large codebases, lunch-break indexing 📚 LEANN ~4h The next best thing I could find in Github CodeGraph Advantages ✅ Incremental Updates: Only reprocess changed files (LEANN can't do this) ✅ Provider Choice: Speed vs. quality optimization based on needs ✅ Memory Optimization: Automatic optimisations based on your system ✅ Production Ready: Index 2.5M lines while having lunch Read the README.md carefully the installation is complex and requires you to download the embedding model in onnx format and Ollama and setting up multiple environment variables (I would recommend setting these in your bash configuration)

Categories

developer-tools

Tags

graphDB

semantic analysis

code understanding

coding agents

Visit Codegraph Mcp 👉

What is Codegraph MCP?

Codegraph MCP is a revolutionary AI development intelligence platform that transforms any MCP-compatible LLM into a codebase expert through advanced semantic analysis. It is designed to index and query large codebases using natural language, providing deep insights before development or changes.

How to use Codegraph MCP?

To use Codegraph MCP, initialize your project with the command codegraph init, index your codebase with codegraph index ., and start the MCP server using codegraph start stdio. You can then query your codebase using natural language.

Key features of Codegraph MCP?

  • Supports multiple programming languages including TypeScript, JavaScript, Rust, Go, Python, and C++.
  • Provides semantic intelligence for understanding codebases.
  • Allows impact prediction before code modifications.
  • Offers intelligent caching and pattern detection for team coding conventions.
  • Incremental updates to only reprocess changed files.

Use cases of Codegraph MCP?

  1. Analyzing coding patterns and architecture in large codebases.
  2. Predicting the impact of changes before they are made.
  3. Generating code that follows team-specific patterns.
  4. Providing architectural insights that are not possible with generic AI.

FAQ from Codegraph MCP?

  • Can Codegraph MCP work with any programming language?

    Currently, it supports 11 programming languages with advanced semantic analysis for 8 and basic analysis for 3.

  • Is Codegraph MCP free to use?

    The project is open-source and available for free on GitHub.

  • How accurate is the semantic analysis?

    The accuracy depends on the complexity of the codebase and the quality of the embeddings used.

View More