Die besten MCP-Server für OpenAI Codex (2026)
Das sind die 30 beliebtesten Open-Source-MCP-Server für OpenAI Codex, sortiert nach GitHub-Sternen. Jeder Eintrag verlinkt auf eine Seite mit Repository-Details, Installationskonfiguration (falls vorhanden) und ähnlichen Servern.
- Git (official) Official – Tools to read, search, and manipulate Git repositories.
- Everything (official) Official – Reference / test server with prompts, resources, and tools.
- ruflo ★74716 – 🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conver
- context7 ★63053 – Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
- chrome-devtools-mcp ★53561 – Chrome DevTools for coding agents
- codebase-memory-mcp ★46616 – High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in mil
- github-mcp-server ★33624 – GitHub's official MCP Server
- serena ★30270 – A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
- context-mode ★29327 – Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and
- activepieces ★25058 – AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI W
- n8n-mcp ★23073 – A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
- Auto-claude-code-research-in-sleep ★17502 – ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops
- hexstrike-ai ★12794 – HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+
- mcp-use ★10763 – The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.
- Trail-Code ★10038 – Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding spec
- MobileBuildMCP ★6480 – A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
- semble ★6209 – Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read
- open-seo-mcp-skills ★5546 – Free SEO MCP server + open-source SEO and GEO skills for Claude: keyword research, rank tracking, audits, backlinks, AI
- zotero-mcp ★5398 – Zotero MCP: Connects your Zotero research library with Claude and other AI assistants via the Model Context Protocol to
- code-graph-rag ★5258 – The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowle
- exa-mcp-server ★5131 – Exa MCP for web search and web crawling!
- tradingview-mcp ★5061 – TradingView MCP server — real-time market data, technical analysis, screeners & backtesting for Claude, ChatGPT, Cursor
- marketing-skills ★4617 – Claude skills for marketing: 49 free marketing skills for Claude Code and claude.ai (Google Ads, Meta Ads, SEO, AI visib
- Unity-MCP ★4461 – AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token
- excel-mcp-server ★4241 – Excel MCP server: let AI (Claude, Cursor, Codex) create and edit Excel files with charts, PivotTables, slicers and formu
- design-extract ★4237 – Extract any website's complete design system with one command. DTCG tokens, semantic+primitive+composite, MCP server for
- fast-agent ★3936 – Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support
- linkedin-mcp-server ★3875 – Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, an
- hyperresearch ★3856 – Convert Claude Code or Codex into the most intelligent Deep Research Agent. Collect, search, and synthesize web research
- pipeshub-ai ★3833 – The open-source context layer for AI agents. PipesHub turns your company's knowledge (Slack, Drive, Jira, GitHub, Micros
Häufige Fragen
Was ist ein MCP-Server für OpenAI Codex?
Ein MCP-Server (Model Context Protocol) verbindet KI-Assistenten wie Claude, Cursor oder GitHub Copilot in VS Code mit externen Tools und Daten. Die Server auf dieser Seite sind auf OpenAI Codex ausgerichtet.
Wie wird diese Liste sortiert?
Nach GitHub-Sternen und aktueller Aktivität, auf Basis öffentlicher Repository-Daten vom 15. Oktober 2026.
Wie installiere ich einen Server?
Die meisten Server trägst du als npx-, uvx- oder Docker-Befehl in die MCP-Konfigurationsdatei deines Clients ein. Unsere Anleitungen für Claude Desktop, Cursor und VS Code zeigen das Schritt für Schritt.
Passende Anleitungen
- MCP-Server in Claude Desktop installieren (Schritt für Schritt)
- MCP-Server in Cursor installieren (Anleitung zu mcp.json)
- MCP-Server in VS Code mit GitHub Copilot nutzen
Wöchentlicher MCP-Überblick – neue und angesagte MCP-Server direkt ins Postfach.