Servidores MCP
El registro abierto de servidores Model Context Protocol. Encuentra herramientas, recursos y prompts para tus agentes de IA, filtrados por categoría, transporte o caso de uso.
Algunas descripciones forman parte del piloto de traducción automática y aún no han sido revisadas.
Servidores
177
Herramientas
471
Categorías
11
Colaboradores
155
Official Zapier MCP server that exposes thousands of app integrations and Zap actions to AI agents through a single remote endpoint. Lets agents trigger automations and perform actions across apps like Gmail, Slack, Google Sheets, and Salesforce without building custom integrations, with per-action scoping configured in the Zapier dashboard.
Official Apify MCP server that gives AI agents access to thousands of Actors for web scraping and automation. Agents can run Actors to extract data from websites, search engines, social platforms, and maps, then retrieve structured results from the dataset, enabling rich web research and data collection.
Official MCP server for the Stripe API. Enables AI agents to interact with Stripe's payment infrastructure including creating and managing customers, payment intents, subscriptions, invoices, and products. Supports reading transaction data, handling refunds, and querying balance information. Useful for building payment integrations, debugging billing issues, and automating financial operations.
Official Plaid MCP server for financial data connectivity. Lets AI agents work with Plaid's APIs to retrieve accounts, balances, and transactions, and to build and debug integrations for banking, payments, and identity. Useful for fintech development, personal finance tooling, and automating account data workflows.
Apollo's official MCP server that exposes GraphQL operations as MCP tools, letting AI agents interact with any GraphQL API through the Model Context Protocol. Turns curated GraphQL operations into callable tools, supports schema introspection, and can run locally alongside a graph via the Rover CLI or in production with the Apollo Runtime Container.
Postman's official MCP server that connects the Postman platform to AI tools. Gives agents the ability to access workspaces, manage collections and environments, work with API specifications, run requests, and automate API workflows through natural language. Useful for exploring, testing, and maintaining APIs directly from an MCP-compatible assistant.
The official Shopify Dev MCP server, built by Shopify, gives AI coding tools direct access to Shopify's developer platform. Agents can search Shopify documentation, explore and introspect the Admin and Storefront GraphQL API schemas, validate GraphQL operations, and scaffold Functions — keeping answers grounded in up-to-date, accurate Shopify APIs.
Provides HTTP request capabilities through the Model Context Protocol. Enables AI agents to fetch web content, retrieve API responses, and download resources from URLs. Supports converting HTML to Markdown for easier consumption and can handle various content types including JSON, text, and binary data.
Microsoft's official Playwright MCP server that provides browser automation capabilities for AI agents. Enables navigating web pages, clicking elements, filling forms, taking screenshots, and extracting content. Supports headless and headed modes with Chromium, Firefox, and WebKit browsers. Ideal for web testing, scraping, and interactive browsing tasks.
Provides access to AWS documentation and service information through the Model Context Protocol. Enables AI agents to search AWS documentation, retrieve service descriptions, look up API references, and find best practices for AWS services. Part of the official AWS Labs MCP servers collection with multiple AWS-focused servers available.
MCP server for Exa's neural search API. Provides AI agents with powerful web search capabilities using embeddings-based semantic search. Returns clean, parsed content from web pages with relevance scoring. Supports filtering by domain, date range, and content type for precise information retrieval from the internet.
MCP server for Firecrawl's web scraping and crawling API. Converts any website into clean, LLM-ready markdown or structured data. Supports single page scraping, multi-page crawling with depth control, sitemap-based extraction, and batch operations. Handles JavaScript-rendered pages, bypasses common anti-bot measures, and returns structured content suitable for RAG pipelines and knowledge base construction.
Official MCP server for the Perplexity API Platform. Provides AI agents with real-time web search, deep research, and advanced reasoning capabilities through Sonar models. Includes tools for quick web search, conversational Q&A with citations, comprehensive deep research reports, and complex analytical reasoning. Returns answers with source attribution and supports configurable timeouts for long research queries.
MCP server for Gmail that lets AI agents read, search, draft, and send email, manage labels, and organize the inbox via the Gmail API with OAuth. Handy for triaging mail, drafting replies, and automating routine inbox workflows from an AI client.
A powerful, native Go implementation of a Kubernetes MCP server with support for Kubernetes and OpenShift. Unlike kubectl wrappers, it interacts directly with the Kubernetes API server — no external CLI tools required. Distributed as a single lightweight binary for Linux, macOS, and Windows. Supports multi-cluster configurations, Helm chart management, Tekton pipelines, pod exec, log streaming, and optional OpenTelemetry distributed tracing.
MCP server for Obsidian that connects AI agents to a local Markdown knowledge vault via the Local REST API plugin. Lets agents read, search, create, and update notes, follow links, and manage frontmatter and tags. Useful for personal knowledge management, note synthesis, and grounding agents in your own notes.
MCP server for Google Calendar that lets AI agents view, create, update, and delete events, check availability across calendars, and schedule meetings via the Calendar API with OAuth. Useful for natural-language scheduling and calendar management.
Official Hugging Face MCP Server that connects AI assistants directly to the Hugging Face Hub ecosystem. Provides tools for searching and retrieving models, datasets, and research papers, running inference on thousands of Gradio-powered AI applications (Spaces), and accessing the full Hub API. Supports remote HTTP-streaming via https://huggingface.co/mcp with OAuth or Bearer token auth, as well as local stdio deployment. Works with Claude, Gemini CLI, VS Code, Cursor, and any MCP-compatible client.
Official Browserbase MCP server for cloud browser automation. Lets AI agents create headless browser sessions, navigate pages, extract content, take screenshots, and perform actions using Stagehand, enabling reliable web automation and scraping at scale from AI-powered tools.
Ofrece funciones completas de búsqueda mediante Brave Search API y Model Context Protocol. Permite a los agentes de IA realizar búsquedas web, de negocios locales, imágenes, vídeos y noticias, además de generar resúmenes con IA. Admite transportes STDIO y HTTP.
Official Atlassian Rovo MCP Server — a cloud-based bridge between Atlassian Cloud and any MCP-compatible AI tool. Enables AI agents to search, summarize, create, and update Jira issues, Confluence pages, and Compass components in real-time. Uses OAuth 2.1 or API token authentication, respects existing user permissions, and supports remote HTTP-streaming as well as local stdio via the mcp-remote proxy. Works with Claude, GitHub Copilot, Gemini CLI, VS Code, Cursor, and ChatGPT.
Skills frente a servidores MCP
¿cuál es la diferencia?Skillsel «qué hacer»
Una Skill reúne conocimientos prácticos —instrucciones, un prompt de ejemplo y modelos recomendados— para que un agente realice una tarea de forma consistente. Las Skills aportan conocimiento, no nuevas conexiones.
Servidores MCPel «cómo conectarse»
Un servidor MCP proporciona nuevas capacidades a un agente conectándolo con sistemas reales —bases de datos, API o archivos— mediante un transporte. MCP añade conexiones y acciones, no instrucciones de tarea.
Regla práctica: usa una Skill cuando necesites que el modelo realice bien una tarea y un servidor MCP cuando necesites conectarlo con una herramienta o sistema. Se complementan: una Skill puede utilizar las herramientas que proporciona un servidor MCP.
¿Has creado un servidor MCP?
Envíalo al registro: es de código abierto y está mantenido por la comunidad.