{
 "schema_version": 1,
 "generated": "2026-10-27",
 "url": "https://dedupedai.com/best-ai-repos-for/mcp-servers/",
 "task": "MCP servers",
 "question": "What are the best open-source MCP servers?",
 "answer": "The best open-source AI repos for MCP servers right now are GitHub MCP Server, Playwright MCP and Chrome DevTools MCP. The most useful first MCP servers connect your agent to tools you already use: GitHub MCP Server for repos, issues and pull requests, Playwright MCP or Chrome DevTools MCP for the browser, and Firecrawl for the web.",
 "md": "https://dedupedai.com/best-ai-repos-for/mcp-servers/index.md",
 "repos": [
  {
   "repo": "github/github-mcp-server",
   "title": "GitHub MCP Server",
   "url": "https://dedupedai.com/use-cases/github-github-mcp-server/",
   "github": "https://github.com/github/github-mcp-server",
   "what": "The GitHub MCP Server is GitHub's official server that connects AI tools to GitHub. Agents can browse and search code, manage issues and pull requests, watch GitHub Actions runs and analyze failures, review Dependabot alerts and security findings, and work with discussions and notifications. You can use the remote server hosted by GitHub or run it locally in Docker with a personal access token, and turn toolsets on or off.",
   "who": "Developers and maintainers who want their agent or chatbot to work with issues, PRs and CI on GitHub directly.",
   "stars": 33932,
   "language": "Go",
   "requirements": [
    "A GitHub account",
    "An MCP host such as VS Code, Claude Code or Cursor",
    "For local use: Docker and a GitHub personal access token"
   ],
   "uc_count": 3,
   "use_cases": [
    {
     "title": "Connect your agent to GitHub with the hosted MCP server",
     "url": "https://dedupedai.com/use-cases/github-github-mcp-server/connect-your-agent-to-github-remotely/"
    },
    {
     "title": "Find out why a GitHub Actions run failed",
     "url": "https://dedupedai.com/use-cases/github-github-mcp-server/triage-a-failing-github-actions-run/"
    },
    {
     "title": "Run the GitHub MCP server locally in Docker",
     "url": "https://dedupedai.com/use-cases/github-github-mcp-server/run-the-github-mcp-server-locally-in-docker/"
    }
   ],
   "best": {
    "title": "Connect your agent to GitHub with the hosted MCP server",
    "url": "https://dedupedai.com/use-cases/github-github-mcp-server/connect-your-agent-to-github-remotely/",
    "difficulty": "Beginner",
    "time": "10 minutes",
    "agents": [
     "claude-code",
     "cursor",
     "codex"
    ],
    "steps": [
     "Add a server named github of type http with the URL https://api.githubcopilot.com/mcp/ to your host's MCP config",
     "Sign in with OAuth, or pass a personal access token in the Authorization header",
     "Ask the agent about open issues, recent commits or a PR"
    ],
    "md": "https://dedupedai.com/use-cases/github-github-mcp-server/connect-your-agent-to-github-remotely/index.md"
   }
  },
  {
   "repo": "microsoft/playwright-mcp",
   "title": "Playwright MCP",
   "url": "https://dedupedai.com/use-cases/microsoft-playwright-mcp/",
   "github": "https://github.com/microsoft/playwright-mcp",
   "what": "Playwright MCP is Microsoft's MCP server for browser automation with Playwright. It lets an LLM work with web pages through structured accessibility snapshots instead of screenshots, so no vision model is needed. It installs with one npx command in Claude Code, Codex, Cursor, VS Code, Amp and other clients, and supports Chrome, Firefox, WebKit and Edge. The README suggests the Playwright CLI with skills for token-heavy coding agent work and MCP for exploratory, stateful agent loops.",
   "who": "Developers and QA engineers who want an agent to click through a web app, test flows or collect data in a real browser.",
   "stars": 38601,
   "language": "TypeScript",
   "requirements": [
    "Node.js",
    "An MCP client such as Claude Code, Codex, Cursor or VS Code"
   ],
   "uc_count": 3,
   "use_cases": [
    {
     "title": "Give Claude Code or Codex a real browser in one command",
     "url": "https://dedupedai.com/use-cases/microsoft-playwright-mcp/add-a-browser-to-claude-code-or-codex/"
    },
    {
     "title": "Let an agent explore and test a signup or checkout flow",
     "url": "https://dedupedai.com/use-cases/microsoft-playwright-mcp/explore-and-test-a-signup-flow-with-an-agent/"
    },
    {
     "title": "Check your site in Firefox, WebKit or Edge through your agent",
     "url": "https://dedupedai.com/use-cases/microsoft-playwright-mcp/run-playwright-mcp-in-firefox-or-webkit/"
    }
   ],
   "best": {
    "title": "Give Claude Code or Codex a real browser in one command",
    "url": "https://dedupedai.com/use-cases/microsoft-playwright-mcp/add-a-browser-to-claude-code-or-codex/",
    "difficulty": "Beginner",
    "time": "5 minutes",
    "agents": [
     "claude-code",
     "codex",
     "cursor"
    ],
    "steps": [
     "Claude Code: claude mcp add playwright npx @playwright/mcp@latest",
     "Codex: codex mcp add playwright npx \"@playwright/mcp@latest\"",
     "Other clients: add an mcpServers entry named playwright that runs npx with @playwright/mcp@latest",
     "Ask the agent to open your app and walk through a flow"
    ],
    "md": "https://dedupedai.com/use-cases/microsoft-playwright-mcp/add-a-browser-to-claude-code-or-codex/index.md"
   }
  },
  {
   "repo": "ChromeDevTools/chrome-devtools-mcp",
   "title": "Chrome DevTools MCP",
   "url": "https://dedupedai.com/use-cases/chromedevtools-chrome-devtools-mcp/",
   "github": "https://github.com/ChromeDevTools/chrome-devtools-mcp",
   "what": "Chrome DevTools for agents (chrome-devtools-mcp) lets a coding agent such as Claude, Cursor, Copilot or Antigravity control and inspect a live Chrome browser, as an MCP server or as a CLI. The agent can record performance traces and get insights, read network requests and console messages with source-mapped stack traces, take screenshots, and automate pages with Puppeteer. The README warns that it exposes the browser's content to the MCP client, so avoid sensitive sites in that browser.",
   "who": "Web developers who want their coding agent to see what the page actually does in Chrome instead of guessing from source.",
   "stars": 54099,
   "language": "TypeScript",
   "requirements": [
    "Node.js and npm",
    "Chrome",
    "An MCP client or a coding agent that can run shell commands"
   ],
   "uc_count": 3,
   "use_cases": [
    {
     "title": "Let your coding agent debug a page in a real Chrome",
     "url": "https://dedupedai.com/use-cases/chromedevtools-chrome-devtools-mcp/let-your-agent-debug-a-page-in-real-chrome/"
    },
    {
     "title": "Have an agent record a performance trace and explain it",
     "url": "https://dedupedai.com/use-cases/chromedevtools-chrome-devtools-mcp/get-performance-insights-from-a-trace/"
    },
    {
     "title": "Drive Chrome from the command line with the DevTools CLI skill",
     "url": "https://dedupedai.com/use-cases/chromedevtools-chrome-devtools-mcp/drive-chrome-from-the-cli-with-a-skill/"
    }
   ],
   "best": {
    "title": "Let your coding agent debug a page in a real Chrome",
    "url": "https://dedupedai.com/use-cases/chromedevtools-chrome-devtools-mcp/let-your-agent-debug-a-page-in-real-chrome/",
    "difficulty": "Beginner",
    "time": "10 minutes",
    "agents": [
     "claude-code",
     "cursor",
     "gemini-cli"
    ],
    "steps": [
     "Add an mcpServers entry named chrome-devtools that runs npx with chrome-devtools-mcp@latest",
     "Restart your MCP client so the tools load",
     "Ask the agent to open your local app and report console messages and failed network requests",
     "Have it fix the cause and take a screenshot to confirm"
    ],
    "md": "https://dedupedai.com/use-cases/chromedevtools-chrome-devtools-mcp/let-your-agent-debug-a-page-in-real-chrome/index.md"
   }
  },
  {
   "repo": "firecrawl/firecrawl",
   "title": "Firecrawl",
   "url": "https://dedupedai.com/use-cases/firecrawl-firecrawl/",
   "github": "https://github.com/firecrawl/firecrawl",
   "what": "Firecrawl is an API that searches, scrapes, crawls and interacts with the web and returns clean markdown, structured JSON or screenshots for AI agents. It handles JavaScript-heavy pages, proxies and rate limits, parses PDFs and DOCX, can click and type before extracting, and plugs into agents as a skill or an MCP server. It is open source and also offered as a hosted service with an API key.",
   "who": "Developers building AI agents, RAG pipelines or research tools that need clean page content instead of raw HTML.",
   "stars": 195071,
   "language": "TypeScript",
   "requirements": [
    "A Firecrawl API key from the hosted service, or a self-hosted instance",
    "Python, Node.js, or curl; or an MCP client such as Claude Code or Cursor"
   ],
   "uc_count": 3,
   "use_cases": [
    {
     "title": "Turn any web page into clean markdown for an LLM",
     "url": "https://dedupedai.com/use-cases/firecrawl-firecrawl/turn-any-url-into-clean-markdown/"
    },
    {
     "title": "Give Claude Code or Cursor live web search and scraping",
     "url": "https://dedupedai.com/use-cases/firecrawl-firecrawl/give-your-coding-agent-live-web-access/"
    },
    {
     "title": "Crawl a whole docs site into a knowledge base",
     "url": "https://dedupedai.com/use-cases/firecrawl-firecrawl/crawl-a-docs-site-into-a-knowledge-base/"
    }
   ],
   "best": {
    "title": "Turn any web page into clean markdown for an LLM",
    "url": "https://dedupedai.com/use-cases/firecrawl-firecrawl/turn-any-url-into-clean-markdown/",
    "difficulty": "Beginner",
    "time": "10 minutes",
    "agents": [],
    "steps": [
     "Get an API key at Firecrawl.dev",
     "Python: from firecrawl import Firecrawl, create app = Firecrawl(api_key=\"fc-YOUR_API_KEY\"), then result = app.scrape('firecrawl.dev')",
     "Or from the CLI: firecrawl https://firecrawl.dev --only-main-content",
     "Ask for other formats such as structured JSON or screenshots when you need them"
    ],
    "md": "https://dedupedai.com/use-cases/firecrawl-firecrawl/turn-any-url-into-clean-markdown/index.md"
   }
  },
  {
   "repo": "ahujasid/mcp-for-blender",
   "title": "MCP for Blender",
   "url": "https://dedupedai.com/use-cases/ahujasid-mcp-for-blender/",
   "github": "https://github.com/ahujasid/mcp-for-blender",
   "what": "MCP for Blender (formerly blender-mcp) connects Blender to any LLM through the Model Context Protocol. A Blender addon runs a socket server and an MCP server connects it to Claude Desktop, Claude Code, Codex, Cursor, VS Code and others, so the AI can create and modify objects, apply materials, check its work with multi-angle views and renders, run Blender Python and pull in Poly Haven, Sketchfab and Poly Pizza assets or AI-generated 3D models.",
   "who": "3D artists, game developers and hobbyists who want to build and edit Blender scenes by describing them in plain language.",
   "stars": 32422,
   "language": "Python",
   "requirements": [
    "Blender",
    "uv (the setup installs it if needed; use the official installer, not pip install uv)",
    "An MCP client such as Claude Desktop, Claude Code, Codex or Cursor",
    "Optional: API access for AI model generators, or the Premium plan"
   ],
   "uc_count": 3,
   "use_cases": [
    {
     "title": "Build a 3D scene in Blender from a text prompt",
     "url": "https://dedupedai.com/use-cases/ahujasid-mcp-for-blender/build-a-blender-scene-from-a-prompt/"
    },
    {
     "title": "Connect Claude Code or Codex to Blender manually",
     "url": "https://dedupedai.com/use-cases/ahujasid-mcp-for-blender/add-mcp-for-blender-to-claude-code/"
    },
    {
     "title": "Populate a scene with Poly Haven and Sketchfab assets",
     "url": "https://dedupedai.com/use-cases/ahujasid-mcp-for-blender/populate-a-scene-with-free-assets/"
    }
   ],
   "best": {
    "title": "Build a 3D scene in Blender from a text prompt",
    "url": "https://dedupedai.com/use-cases/ahujasid-mcp-for-blender/build-a-blender-scene-from-a-prompt/",
    "difficulty": "Beginner",
    "time": "20 minutes",
    "agents": [
     "claude-code",
     "codex",
     "cursor"
    ],
    "steps": [
     "On macOS or Linux run curl -LsSf https://www.mcp-for-blender.com/install.sh | sh (or uvx mcp-for-blender setup if you already have uv)",
     "Pick the MCP clients to set up; it adds a blender entry and saves a .bak of each config",
     "Fully quit and reopen your AI app, then open Blender; the addon starts its server",
     "Ask the AI to build a scene, for example a low-poly campsite at dusk",
     "Ask for multi-angle views or a render to check the result"
    ],
    "md": "https://dedupedai.com/use-cases/ahujasid-mcp-for-blender/build-a-blender-scene-from-a-prompt/index.md"
   }
  },
  {
   "repo": "mksglu/context-mode",
   "title": "Context Mode",
   "url": "https://dedupedai.com/use-cases/mksglu-context-mode/",
   "github": "https://github.com/mksglu/context-mode",
   "what": "Context Mode is an MCP server and hook set for AI coding agents that keeps raw tool output out of the context window, persists session memory in SQLite, and routes work across many clients.",
   "who": "Developers who use AI coding agents on large codebases and notice their context window filling up during long sessions.",
   "stars": 31762,
   "language": "TypeScript",
   "requirements": [
    "Claude Code v1.0.33+ for the plugin install, or Node.js >= 22.5 (or Bun) for the Gemini CLI setup",
    "An existing AI coding agent session in a project you want to work on"
   ],
   "uc_count": 5,
   "use_cases": [
    {
     "title": "Keep large tool output out of Claude Code's context",
     "url": "https://dedupedai.com/use-cases/mksglu-context-mode/cut-claude-code-context-bloat/"
    },
    {
     "title": "Count or summarize code with one script, not many reads",
     "url": "https://dedupedai.com/use-cases/mksglu-context-mode/run-analysis-as-a-script/"
    },
    {
     "title": "Pick up a coding task after the chat compacts",
     "url": "https://dedupedai.com/use-cases/mksglu-context-mode/resume-after-context-compaction/"
    }
   ],
   "best": {
    "title": "Keep large tool output out of Claude Code's context",
    "url": "https://dedupedai.com/use-cases/mksglu-context-mode/cut-claude-code-context-bloat/",
    "difficulty": "Beginner",
    "time": "15 minutes",
    "agents": [
     "claude-code"
    ],
    "steps": [
     "Run /plugin marketplace add mksglu/context-mode in Claude Code.",
     "Run /plugin install context-mode@context-mode.",
     "Restart Claude Code or run /reload-plugins.",
     "Run /context-mode:ctx-doctor and confirm all checks show [x].",
     "Work as usual, then run /context-mode:ctx-stats to see context savings by tool."
    ],
    "md": "https://dedupedai.com/use-cases/mksglu-context-mode/cut-claude-code-context-bloat/index.md"
   }
  }
 ]
}