ThinkyMiner/codeTree
MCP server with 23 tools for structured code understanding via tree-sitter. 10 languages. 999 tests. One-command install.
This project helps software developers improve how their AI coding agents understand and interact with large codebases. By feeding your agent the complete structure of your code, instead of raw files, it allows for more precise questions and interactions. This means your agent can quickly grasp the layout of classes, functions, and their relationships, consuming far fewer 'tokens' and operating more efficiently.
Use this if you are a software developer frequently using AI coding agents (like Claude or Copilot) to navigate, understand, or modify existing codebases and want to make their interactions more efficient and accurate.
Not ideal if you are not using AI coding agents for development, or if you primarily work on very small projects where the overhead of an agent reading full files is negligible.
Stars
15
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/ThinkyMiner/codeTree"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
bgauryy/octocode-mcp
MCP server for semantic code research and context generation on real-time using LLM patterns |...
DeusData/codebase-memory-mcp
MCP server that indexes your codebase into a persistent knowledge graph. 64 languages, sub-ms...
Azure-Samples/snippy
🧩 Build AI-powered MCP Tools with Azure Functions, Durable Agents & Cosmos vector search....
aimasteracc/tree-sitter-analyzer
A scalable, multi-language code analysis framework based on Tree-sitter, usable both as a CLI...
wrale/mcp-server-tree-sitter
MCP Server for Tree-sitter