AI channel
MCP servers

Open-source MCP servers

MCP, the Model Context Protocol, is an open standard for connecting AI assistants to outside tools and data. An MCP server exposes something, such as a database, a browser, a GitHub account or a folder of files, as tools the assistant can call. Clients such as Claude Desktop, Cursor and VS Code load these servers.

How to choose

Check what a server can reach before you install it. One that can run shell commands or write files has all the power of the account it runs under, so prefer servers that ask for the narrowest access: read-only tokens and a single folder. Also check whether it runs locally over stdio or as a remote service you would have to trust.

Most-starred projects

625–634 of 634
mrpulor-gh

nuphus-mcp

★ 316

Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio). Not a DSH plugin — DSH users install dsh-nuphus-mcp.

Rust
★ 316

Postman MCP Server — connect AI agents (Claude Code, Cursor, VS Code Copilot, Gemini CLI) to your Postman collections, OpenAPI specs, and environments via Model Context Protocol (MCP)

TypeScript
★ 315

A Model Context Protocol (MCP) server that enables LLMs to interact with iOS simulators through natural language commands.

TypeScript
shlokkhemani

rabbithole

★ 315

An infinite canvas for learning — select text, ask, and answers branch out as documents. MCP server for Claude Code, Codex, and any agent.

JavaScript
★ 314

A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and multi-agent architecture. Current trend focus: Gemini Interactions API and managed agents, emerging agent runtimes, and production AI workflow patterns.

MDX
★ 313

Servidor MCP fiscal brasileiro: CNPJ, NF-e, NFS-e, CT-e, SPED, eSocial, Simples Nacional, Reforma 2026. 44 tools, zero-cadastro, tabelas offline. Python.

Python
★ 312

A free, self-paced 24-week AI engineering course: Python, machine learning, LLMs, RAG, fine-tuning, agents and MCP, Azure and Vertex and Bedrock, and Databricks. 43 runnable notebooks, one continuous case study. MIT licensed, no signup. By Zorost Intelligence AI Lab.

Jupyter Notebook
zhimaAi

ChatClaw

★ 308

ChatClaw: Get OpenClaw-like knowledge base personal AI agent in 5 mins. Sandbox-secured, ultra-small 30MB installer for macOS & Windows (install in 1 min). Connects to WhatsApp, Telegram, Slack, Discord, Gmail, DingTalk, WeChat Work, QQ, Feishu. Built-in Skill Market, Knowledge Base, Memory, MCP, Scheduled Tasks. Developed in Go ,run

Go
★ 304

This Agent MCP allows you to train external intelligence with zero GPU and let you trade it at Tetrees EX

TypeScript
KevRojo

Dulus

★ 92

Dulus Ai — Agentic AI, Making Gemini web cappable of running bash commands in your terminal! [Gui, Web, Cli, Telegram, 2,000 MCP, 100K Skills . LiteLLM (100+ providers), local models via Ollama, /lang in 34 languages, Mesa Redonda, I create the first utility coin that can be used 100% as AI quota or Fuel, is called $Dulus

Python