# #mcp — GitHub repositories

> Curated open-source repositories tagged "mcp".

- [n8n-io/n8n](https://github.com/n8n-io/n8n) — Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations. (★210k, TypeScript, vibe 99/100) · details: https://ideas.asveas.com/r/n8n-io/n8n
- [langgenius/dify](https://github.com/langgenius/dify) — Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack. (★161k, Python, vibe 98/100) · details: https://ideas.asveas.com/r/langgenius/dify
- [open-webui/open-webui](https://github.com/open-webui/open-webui) — User-friendly AI Interface (Supports Ollama, OpenAI API, ...) (★158k, Svelte, vibe 98/100) · details: https://ideas.asveas.com/r/open-webui/open-webui
- [browser-use/browser-use](https://github.com/browser-use/browser-use) — Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API. (★121k, Python, vibe 97/100) · details: https://ideas.asveas.com/r/browser-use/browser-use
- [google-gemini/gemini-cli](https://github.com/google-gemini/gemini-cli) — An open-source AI agent that brings the power of Gemini directly into your terminal. (★109k, TypeScript, vibe 96/100) · details: https://ideas.asveas.com/r/google-gemini/gemini-cli
- [unclecode/crawl4ai](https://github.com/unclecode/crawl4ai) — Official Crawl4AI Cloud: a hosted web scraping, extraction, and search API for AI agents. Free API key, 1,000 credits a month, no card. Fully open source: this repo is the Apache-2.0 crawler that powers it, and you can self-host it. (★87.2k, Python, vibe 95/100) · details: https://ideas.asveas.com/r/unclecode/crawl4ai
- [lobehub/lobehub](https://github.com/lobehub/lobehub) — 🤯 LobeHub - Super-Agents on Your Team. Add super-agents to the chats your team already uses.They take on work by themselves and get better every week. (★85k, TypeScript, vibe 95/100) · details: https://ideas.asveas.com/r/lobehub/lobehub
- [heygen-com/hyperframes](https://github.com/heygen-com/hyperframes) — Write HTML. Render video. Built for agents. (★82.8k, TypeScript, vibe 95/100) · details: https://ideas.asveas.com/r/heygen-com/hyperframes
- [upstash/context7](https://github.com/upstash/context7) — Context7 Platform -- Up-to-date docs for AI agents (★64.6k, TypeScript, vibe 94/100) · details: https://ideas.asveas.com/r/upstash/context7
- [mudler/LocalAI](https://github.com/mudler/LocalAI) — LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required. (★50.3k, Go, vibe 93/100) · details: https://ideas.asveas.com/r/mudler/LocalAI
- [punkpeye/awesome-mcp-servers](https://github.com/punkpeye/awesome-mcp-servers) — A collection of MCP servers. (★97.6k, vibe 92/100) · details: https://ideas.asveas.com/r/punkpeye/awesome-mcp-servers
- [modelcontextprotocol/servers](https://github.com/modelcontextprotocol/servers) — Model Context Protocol Reference Servers (★91.9k, TypeScript, vibe 91/100) · details: https://ideas.asveas.com/r/modelcontextprotocol/servers
- [mastra-ai/mastra](https://github.com/mastra-ai/mastra) — Mastra is the modern TypeScript framework for AI-powered applications and agents. (★29.5k, TypeScript, vibe 90/100) · details: https://ideas.asveas.com/r/mastra-ai/mastra
- [PrefectHQ/fastmcp](https://github.com/PrefectHQ/fastmcp) — 🚀 The fast, Pythonic way to build MCP servers and clients. (★28.4k, Python, vibe 90/100) · details: https://ideas.asveas.com/r/PrefectHQ/fastmcp
- [activepieces/activepieces](https://github.com/activepieces/activepieces) — AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents (★25.5k, TypeScript, vibe 89/100) · details: https://ideas.asveas.com/r/activepieces/activepieces
- [modelcontextprotocol/python-sdk](https://github.com/modelcontextprotocol/python-sdk) — The official Python SDK for Model Context Protocol servers and clients (★24.8k, Python, vibe 89/100) · details: https://ideas.asveas.com/r/modelcontextprotocol/python-sdk
- [microsoft/playwright-mcp](https://github.com/microsoft/playwright-mcp) — Playwright MCP server (★39.5k, TypeScript, vibe 87/100) · details: https://ideas.asveas.com/r/microsoft/playwright-mcp
- [github/github-mcp-server](https://github.com/github/github-mcp-server) — GitHub's official MCP Server (★34.4k, Go, vibe 87/100) · details: https://ideas.asveas.com/r/github/github-mcp-server
- [triggerdotdev/trigger.dev](https://github.com/triggerdotdev/trigger.dev) — Trigger.dev – build and deploy durable AI agents and workflows (★16.7k, TypeScript, vibe 87/100) · details: https://ideas.asveas.com/r/triggerdotdev/trigger.dev
- [modelcontextprotocol/typescript-sdk](https://github.com/modelcontextprotocol/typescript-sdk) — The official TypeScript SDK for Model Context Protocol servers and clients (★13.7k, TypeScript, vibe 86/100) · details: https://ideas.asveas.com/r/modelcontextprotocol/typescript-sdk
- [modelcontextprotocol/inspector](https://github.com/modelcontextprotocol/inspector) — Deterministic testing tools for MCP servers (★11.3k, TypeScript, vibe 86/100) · details: https://ideas.asveas.com/r/modelcontextprotocol/inspector

---
Source: https://ideas.asveas.com/t/mcp · 21 repositories · Catalog: https://ideas.asveas.com/llms.txt