kiliman/codemesh
The Self-Improving MCP Server - Agents write code to orchestrate multiple MCP servers with intelligent TypeScript execution and auto-augmentation
This project helps AI agents collaborate and perform complex tasks by allowing them to write and execute TypeScript code across various MCP servers. You provide a single prompt, and the system automatically figures out which tools to use, writes the necessary code, and runs it to deliver the desired results. This is designed for developers or anyone building sophisticated AI agent systems that need to integrate multiple services and learn from past interactions.
Available on npm.
Use this if you are building AI agents that need to orchestrate multiple tools, learn from their interactions, and dynamically generate code to solve problems.
Not ideal if you are looking for a simple API wrapper for a single tool or a no-code solution for basic automation.
Stars
23
Forks
4
Language
TypeScript
License
MIT
Category
Last pushed
Nov 03, 2025
Commits (30d)
0
Dependencies
8
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/kiliman/codemesh"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related servers
mcp-use/mcp-use
The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.
TencentCloudBase/CloudBase-MCP
CloudBase MCP - Connect CloudBase to your AI Agent. Go from AI prompt to live app.
zhizhuodemao/js-reverse-mcp
为 AI Agent 设计的 JS 逆向 MCP Server，内置反检测，基于 chrome-devtools-mcp 重构 | JS reverse engineering MCP...
casibase/casibase
⚡️AI Cloud OS: Open-source enterprise-level AI knowledge base and MCP...
juspay/neurolink
Universal AI Development Platform with MCP server integration, multi-provider support, and...