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
175
Tools
465
Categories
11
Contributors
153
MCP server for searching and accessing arXiv research papers. Enables AI agents to search papers with filters for date ranges and categories, download full paper content, read papers in markdown format, and perform semantic search across locally stored papers. Supports citation graph exploration via Semantic Scholar and research alert watches for tracking new publications on topics of interest.
Cloudinary's official MCP servers for managing media through conversational AI. Cover the full media workflow: uploading and transforming images and videos, organizing assets with structured metadata, configuring processing pipelines, and running AI-powered content analysis. Available as remote OAuth endpoints or local npx processes across several focused servers (asset management, environment config, structured metadata, and analysis).
Directus' MCP integration connects agents to headless CMS data, schemas, and operations for governed content and application workflows.
Sanity's official MCP server that connects structured content to AI agents. Provides tools to run GROQ queries, read and write documents, explore and deploy schemas, manage content releases, and generate images, all with full schema context. Available as a hosted remote server at mcp.sanity.io and works with MCP-compatible clients like Cursor, Claude Code, and VS Code.
Zoom's official remote MCP server, published to the MCP registry, that gives AI agents access to Zoom capabilities over the Model Context Protocol. Supports semantic meeting search, Zoom-wide chat and docs search, meeting assets and recording resources, and Zoom Docs import/export, so assistants can find and summarize meeting content and manage related data. Authenticates via OAuth.
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.