Awesome MCP Registry
sunnamed434/awesome-mcp-registry
Diretório auto-curável de servidores MCP ranqueados por IA
Ver no GitHubDiretório auto-atualizável de servidores MCP descobertos do GitHub e registro oficial, analisados e ranqueados por IA semanalmente. Implementa um workflow Continuous AI que julga cada servidor por mérito, sem gatekeepers, usando uma fórmula de confiança transparente e reprodutível.
Instalação
npx convez-ai sunnamed434/awesome-mcp-registry1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Descobrir novos servidores MCP confiáveis para Claude e agentes IA
- Avaliar qualidade e confiabilidade de MCP servers por score publicado
- Acompanhar tendências e inovações no ecossistema MCP automaticamente
Veredito

Prova conceitual ambiciosa de automação de curação via IA. Reduz fricção na descoberta de MCP servers com scoring transparente, embora dependa da qualidade das análises automatizadas e tenha escopo limitado ao ecossistema MCP.
README
A tradução para o português deste README ainda está na fila.
Awesome MCP Registry
A self-curating directory of Model Context Protocol servers — a Continuous AI experiment. Discovered from GitHub and the Official MCP Registry, analyzed by GPT-4.1-mini weekly and scored with a published, reproducible trust formula.
Our bet: curation is a job for AI, not gatekeepers. No maintainers deciding what's "in", no PR queues, no politics — just a Continuous AI workflow that discovers, judges, and re-judges every server on merit, week after week. This list is a small proof of a bigger idea: that AI can own a real, useful, self-maintaining system end to end. Humans set the rules once; the AI runs it.
Databases (4)
| Server | Trust | Stars | Description |
|---|---|---|---|
| mindsdb/mindsdb | 80/100 | 39142 | MindsDB is a federated query engine for AI. |
| googleapis/genai-toolbox | 80/100 | 15101 | An open source MCP server for databases. |
| googleapis/mcp-toolbox | 80/100 | 14415 | MCP Toolbox for Databases is an open source MCP server connecting AI agents to enterprise databases. |
| benborla/mcp-server-mysql | 80/100 | 1246 | MCP server providing read-only access to MySQL databases. |
Dev Tools (29)
| Server | Trust | Stars | Description |
|---|---|---|---|
| github/github-mcp-server | 90/100 | 29669 | GitHub's official MCP Server for AI tool integration. |
| upstash/context7 | 80/100 | 54897 | Context7 Platform for up-to-date code documentation for LLMs and AI code editors. |
| microsoft/playwright-mcp | 80/100 | 32278 | A Model Context Protocol server for browser automation using Playwright. |
| jlowin/fastmcp | 80/100 | 25093 | FastMCP is a Python framework for building MCP servers and applications. |
| oraios/serena | 80/100 | 24020 | A coding agent toolkit providing semantic retrieval and editing capabilities. |
| mksglu/context-mode | 80/100 | 12064 | Context window optimization tool for AI coding agents. |
| hangwin/mcp-chrome | 80/100 | 11637 | Chrome MCP Server is a Chrome extension that enables AI assistants to automate browser tasks. |
| BeehiveInnovations/pal-mcp-server | 80/100 | 11540 | A server that integrates multiple AI models into a cohesive CLI workflow. |
| tadata-org/fastapi_mcp | 80/100 | 11509 | Expose your FastAPI endpoints as Model Context Protocol (MCP) tools. |
| mcp-use/mcp-use | 80/100 | 9962 | Fullstack MCP framework for developing MCP Apps and Servers. |
| LaurieWired/GhidraMCP | 80/100 | 8905 | MCP server for Ghidra enabling autonomous reverse engineering. |
| idosal/git-mcp | 80/100 | 8082 | GitMCP is a remote MCP server for GitHub projects that enhances AI tool access to documentation. |
| wonderwhy-er/DesktopCommanderMCP | 80/100 | 6070 | MCP server for terminal control and file management with AI capabilities. |
| cameroncooke/XcodeBuildMCP | 80/100 | 5792 | A Model Context Protocol server and CLI for iOS and macOS projects. |
| kucherenko/jscpd | 80/100 | 5656 | A copy/paste detector for programming source code with MCP server capabilities. |
| executeautomation/mcp-playwright | 80/100 | 5531 | A Model Context Protocol server for automating browsers using Playwright. |
| CursorTouch/Windows-MCP | 80/100 | 4706 | MCP server for integrating AI agents with Windows OS. |
| getsentry/XcodeBuildMCP | 80/100 | 4287 | MCP server and CLI for iOS and macOS project tools. |
| IBM/mcp-context-forge | 80/100 | 3834 | An AI Gateway that federates MCP, A2A, and REST/gRPC APIs. |
| mattzcarey/shippie | 80/100 | 2327 | Shippie is an extendable code review and QA agent using LLMs. |
...and 9 more. See known_servers.json for the full list.
Cloud (1)
| Server | Trust | Stars | Description |
|---|---|---|---|
| awslabs/mcp | 80/100 | 9069 | Open source MCP servers for AWS. |
Productivity (9)
| Server | Trust | Stars | Description |
|---|---|---|---|
| Pimzino/spec-workflow-mcp | 90/100 | 4212 | A structured spec-driven development workflow MCP server. |
| haris-musa/excel-mcp-server | 90/100 | 3906 | A Model Context Protocol server for Excel file manipulation. |
| GongRzhe/Office-PowerPoint-MCP-Server | 90/100 | 1765 | A comprehensive MCP server for PowerPoint manipulation using python-pptx. |
| czlonkowski/n8n-mcp | 80/100 | 13294 | A MCP server that integrates n8n workflow automation with AI assistants. |
| sooperset/mcp-atlassian | 80/100 | 4754 | MCP server for Atlassian tools like Confluence and Jira. |
| coddingtonbear/obsidian-local-rest-api | 80/100 | 2246 | A secure REST API and MCP server for accessing Obsidian vaults. |
| GongRzhe/Office-Word-MCP-Server | 80/100 | 2030 | An MCP server for creating and manipulating Microsoft Word documents. |
| BigSweetPotatoStudio/HyperChat | 80/100 | 712 | HyperChat is a local AI agent platform utilizing MCP for enhanced chat experiences. |
| supermemoryai/apple-mcp | 70/100 | 2993 | Apple-native tools for enhancing productivity through the Model Context Protocol. |
Communication (1)
| Server | Trust | Stars | Description |
|---|---|---|---|
| lharries/whatsapp-mcp | 80/100 | 5683 | WhatsApp MCP server for managing messages and media. |
Web Scraping (5)
| Server | Trust | Stars | Description |
|---|---|---|---|
| JoeanAmier/XHS-Downloader | 80/100 | 10016 | A tool for extracting and downloading content from XiaoHongShu. |
| D4Vinci/Scrapling | 80/100 | 8937 | A powerful Python library for adaptive web scraping. |
| firecrawl/firecrawl-mcp-server | 80/100 | 6370 | A powerful web scraping and search MCP server for AI agents. |
| epiral/bb-browser | 80/100 | 5612 | CLI + MCP server for AI agents to control Chrome with your login state. |
| brightdata/brightdata-mcp | 80/100 | 2436 | A powerful MCP server for real-time web access and data collection. |
AI & ML (20)
| Server | Trust | Stars | Description |
|---|---|---|---|
| modelscope/FunASR | 90/100 | 16655 | Industrial-grade speech recognition toolkit with multi-language support. |
| activepieces/activepieces | 80/100 | 22123 | Activepieces is an AI automation platform with extensible MCP servers. |
| ruvnet/ruflo | 80/100 | 16632 | Ruflo is an AI orchestration platform for deploying and managing multi-agent systems. |
| chopratejas/headroom | 80/100 | 16123 | Headroom compresses AI agent inputs to reduce token usage. |
| GLips/Figma-Context-MCP | 80/100 | 14691 | MCP server providing Figma data to AI coding agents. |
| ruvnet/claude-flow | 80/100 | 13789 | Claude-Flow is an AI orchestration platform for deploying multi-agent systems. |
| triggerdotdev/trigger.dev | 80/100 | 13583 | Trigger.dev is an open-source platform for building AI workflows in TypeScript. |
| yusufkaraaslan/Skill_Seekers | 80/100 | 9084 | Automated tool to convert documentation into Claude AI skills. |
| kreuzberg-dev/kreuzberg | 80/100 | 8376 | A polyglot document intelligence framework for extracting information from various formats. |
| mrexodia/ida-pro-mcp | 80/100 | 5427 | AI-powered reverse engineering assistant for IDA Pro using MCP. |
| u14app/deep-research | 80/100 | 4588 | A server for generating in-depth research reports using various LLMs. |
| liaokongVFX/MCP-Chinese-Getting-Started-Guide | 80/100 | 3316 | A guide to quickly set up a Model Context Protocol server for web searching. |
| blazickjp/arxiv-mcp-server | 80/100 | 2828 | A Model Context Protocol server for searching and analyzing arXiv papers. |
| Jpisnice/shadcn-ui-mcp-server | 80/100 | 2642 | MCP server for integrating shadcn UI components into AI workflows. |
| perplexityai/modelcontextprotocol | 80/100 | 1950 | Official MCP server implementation for the Perplexity API Platform. |
| stacklok/toolhive | 80/100 | 1665 | ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers. |
| robotmcp/ros-mcp-server | 80/100 | 1010 | Connects AI models with robots using MCP and ROS. |
| bgauryy/octocode-mcp | 80/100 | 725 | MCP server for semantic code research and context generation using LLM patterns. |
| obot-platform/obot | 80/100 | 606 | Obot is a comprehensive platform for hosting and managing MCP servers. |
| truffle-ai/dexto | 70/100 | 580 | Dexto is an agent harness for building and orchestrating AI applications. |
Security (2)
| Server | Trust | Stars | Description |
|---|---|---|---|
| 0x4m4/hexstrike-ai | 90/100 | 8773 | HexStrike AI is an advanced MCP server for automated cybersecurity tasks. |
| casdoor/casdoor | 80/100 | 13033 | An AI-first Identity and Access Management (IAM) / MCP gateway and auth server. |
Media (1)
| Server | Trust | Stars | Description |
|---|---|---|---|
| nukeop/nuclear | 80/100 | 17138 | Nuclear is a free, open-source music player with an MCP server for AI control. |
Knowledge Base (2)
| Server | Trust | Stars | Description |
|---|---|---|---|
| open-metadata/OpenMetadata | 80/100 | 8650 | OpenMetadata is a unified metadata platform for data discovery and governance. |
| datagouv/datagouv-mcp | 80/100 | 1388 | MCP server for exploring French national Open Data datasets via AI chatbots. |
Other (4)
| Server | Trust | Stars | Description |
|---|---|---|---|
| xpzouying/xiaohongshu-mcp | 80/100 | 8777 | MCP server for interacting with xiaohongshu.com |
| webiny/webiny-js | 80/100 | 7955 | Open-source CMS platform with AI-assisted development on AWS. |
| mobile-next/mobile-mcp | 80/100 | 5078 | MCP server for mobile automation and scraping across iOS and Android. |
| zcaceres/markdownify-mcp | 80/100 | 2728 | A Model Context Protocol server for converting various file types to Markdown. |
How This Works
This registry is automatically maintained by a GitHub Actions workflow that runs weekly:
- Discover — searches GitHub and the Official MCP Registry for new servers; community nominations join the same queue
- Analyze — each repo is evaluated by AI (GPT-4.1-mini via GitHub Models) on an anchored rubric, informed by deterministic scanner evidence (MCP SDK dependencies found in the repo's manifests). Prompt-injection attempts are flagged and penalized
- Score — a transparent 0-100 trust score: 35% AI rubric + 65% verifiable metrics (maintenance, popularity, docs, security posture, community). The exact formula is published in METHODOLOGY.md; every server's breakdown is in SCORES.md
- Re-evaluate — the AI re-judges servers every ~90 days; metrics and trust scores refresh every week. Projects that stagnate fall off the list
- Rank — only servers scoring 50+/100 appear here, top 20 per category, sorted by trust then stars
- Exclude — a small human-maintained exclusion list overrides the AI only for spam/scam removals and maintainer opt-outs (see CONTRIBUTING.md)
Servers are curated entirely by AI — they earn their spot through quality and lose it if they fall behind. Maintainers don't hand-pick entries. Every automated change lands as an auto-merged pull request, so the full history stays auditable and revertable.
A Note on Security
Trust scores are computed from public metadata, the README, and OpenSSF Scorecard data. No entry has been code-audited or executed by this registry. A high score means strong public signals, not a security guarantee — review any MCP server (and the credentials you grant it) before connecting it to your tools.
Contributing
Don't open a pull request to add a server. This README is generated from data/known_servers.json on every run, so edits to it are overwritten — and such PRs are closed automatically.
To suggest a server, open a nomination. The same AI evaluates it on the next weekly run and posts the verdict; if it scores 50+/100 it appears here automatically.
Code contributions (bug fixes, scanner improvements) are welcome — see CONTRIBUTING.md.