MCP Servers
The open registry for Model Context Protocol servers. Find the right tools, resources, and prompts for your AI agents — filtered by category, transport, or use case.
Servers
187
Tools
493
Categories
11
Contributors
164
Mapbox's official Model Context Protocol server, giving AI agents access to Mapbox's geospatial APIs. Supports forward and reverse geocoding, routing and directions, isochrone and matrix travel-time computation, and static map image generation, so assistants can answer location questions and build map-driven workflows from natural language.
MCP server for the Google Maps Platform. Enables AI agents to geocode addresses, search for places, retrieve place details, and compute directions and distances, giving models location awareness and routing from AI-powered tools.
Skills vs MCP servers
what’s the difference?Skillsthe “what to do”
A skill packages know-how — instructions, an example prompt, and recommended models — so an agent performs a task consistently. Skills add knowledge, not new connections.
MCP serversthe “how to connect”
An MCP server gives an agent new capabilities by connecting it to real systems (databases, APIs, files) over a transport. MCP adds connections and actions, not task instructions.
Rule of thumb: reach for a skill when you need the model to do a task well, and an MCP server when you need it to reach a tool or system. They compose — a skill can rely on tools an MCP server provides.
Built an MCP server?
Submit it to the registry — it’s open source and community-maintained.