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
92
Tools
343
Categories
11
Contributors
79
Reference MCP server for Git repository operations. Provides tools to read, search, and manipulate Git repositories including viewing commit history, diffs, branches, file contents at specific revisions, and repository status. Enables AI agents to understand code changes and navigate version history without direct filesystem access.
Enables AI agents to interact with Amazon Web Services through the Model Context Protocol. Provides access to core AWS services including S3, Lambda, DynamoDB, CloudWatch, and IAM. Supports resource discovery, log analysis, and infrastructure management with proper credential handling and region awareness.
Official Snyk MCP server that brings developer security scanning into AI agent workflows. Lets agents scan code, open-source dependencies, containers, and infrastructure-as-code for vulnerabilities, retrieve fix advice, and check license issues directly from the editor or CI, using the Snyk CLI under the hood.
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.
E2B's MCP server gives AI agents the ability to run arbitrary code in secure, isolated cloud sandboxes. Each sandbox is a fast-booting micro-VM where models can execute Python and shell commands, install packages, read and write files, and capture stdout/stderr — ideal for code interpretation, data analysis, and agentic workflows that need real execution.
Official Vercel MCP server that gives AI tools secure access to Vercel projects via OAuth. Enables searching Vercel documentation, managing projects and deployments, analyzing deployment logs, and interacting with Vercel infrastructure. Supports Streamable HTTP transport with OAuth authentication and integrates with Claude Code, Cursor, VS Code, ChatGPT, Codex CLI, and other AI assistants.
Official Cloudflare MCP server for managing Cloudflare services. Enables AI agents to interact with Workers, KV namespaces, R2 storage, D1 databases, and DNS records. Supports deploying Workers scripts, managing environment variables, querying analytics, and configuring security settings across Cloudflare's edge network.
MCP server for Neon's serverless PostgreSQL platform. Enables AI agents to manage Neon projects, branches, databases, and roles. Supports creating database branches for development and testing, running SQL queries, managing connection strings, and performing schema migrations. Leverages Neon's instant branching for safe experimentation without affecting production data.
Official Elastic MCP server that connects AI agents to Elasticsearch data using the Model Context Protocol. Enables natural language interactions with Elasticsearch indices — querying, analyzing, and retrieving data without custom APIs. Supports both stdio and streamable-HTTP transports, and works with Elasticsearch 8.x/9.x clusters including Elasticsearch Serverless. Distributed as a Docker container image from the Elastic registry.
Skills vs MCP servers
what's the difference?Skillsthe “what to do”
A skillA reusable, structured prompt/workflow with recommended models, an example prompt, and compatible tools. packages know-how — instructions, an example promptA ready-to-use prompt template that demonstrates how to invoke the skill., and recommended models — so an agent performs a task consistently. Skills add knowledge, not new connections.
MCP serversthe “how to connect”
An MCP serverModel Context Protocol server — a standard way to expose tools, resources, and prompts to AI agents and IDEs. gives an agent new capabilities by connecting it to real systems (databases, APIs, files) over a transportHow the client talks to the server: stdio (local process), SSE, or HTTP streaming.. 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.