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.
Servidores
177
Herramientas
471
Categorías
11
Colaboradores
155
Firebase's MCP integration exposes Firebase project context and development workflows to coding agents for building, testing, and operating Firebase applications.
GrowthBook's official MCP server for working with feature flags, experiments, and metrics so agents can safely support product experimentation workflows.
Harness' official MCP server for connecting agents to software delivery workflows, including deployment pipelines, services, environments, and delivery insights.
JFrog's MCP server lets agents work with Platform services for artifact repositories, build information, release lifecycle management, and software supply-chain workflows.
Official MCP server backed by the Kagi API. Exposes Kagi's high-quality search and summarization tools to MCP-compatible clients, including web search and the Universal Summarizer for pages and videos. Useful for research workflows that want ad-free, privacy-respecting results with concise summaries. Requires a Kagi API key.
MCP server that bridges AI assistants with the Unity Editor. Gives an LLM tools to create and modify GameObjects, edit scripts, manage assets and scenes, read the console, and run tests, enabling AI-driven game development workflows directly inside Unity. Works with clients such as Claude, Cursor, VS Code, and other MCP-compatible tools.
Google's MCP Toolbox provides secure, ready-made and custom tools for database queries, schema operations, and semantic search in agent workflows.
Medusa's MCP integration connects agents to commerce data and administrative operations for storefront, catalog, order, and customer workflows.
MindsDB's MCP integration gives agents access to AI workflows, data integrations, and automation capabilities through the MindHub platform.
Popular community MCP server that gives AI assistants deep knowledge of n8n's workflow automation nodes, their properties, and operations, and can connect to a live n8n instance to create and manage workflows. Helps agents design, validate, and deploy automations correctly by exposing node documentation, validation, and workflow management tools.
OpenBB's MCP server connects agents to financial market data, research, and analytics for evidence-based investment and business workflows.
Payload CMS provides an MCP integration for agents to explore and manage CMS content, schemas, and application workflows.
Pinecone's official MCP server connects AI assistants to Pinecone vector databases for retrieval-augmented generation (RAG) workflows. Lets agents create and configure indexes, upsert and embed documents, and run semantic searches over vector data — all from natural language, without leaving the editor or chat.
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.
Prisma's official MCP server that lets AI tools manage Prisma ORM projects and Prisma Postgres databases through natural language. Provides both a local server for working with a project's Prisma schema and migrations, and a remote server for provisioning and managing Prisma Postgres databases. Useful for scaffolding models, generating and applying migrations, and running database workflows from an AI coding assistant.
MCP server for interacting with a Tinybird Workspace from any MCP client. Lets AI agents explore data sources, call published API endpoints, run SQL queries over real-time data, and push datafiles, making Tinybird's analytics readily available to LLM-driven workflows.
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.