VoltAgent/official-mcp-servers

A curated directory of 390+ official MCP servers from the companies behind the products. No unofficial forks, no abandoned projects.

What it solves

AI assistants like Claude, ChatGPT, or Cursor need to connect to external tools and data (e.g., databases, cloud services, monitoring). The Model Context Protocol (MCP) is an open standard for this, but finding reliable MCP servers is hard: many are unofficial forks or abandoned projects. This project solves that by curating a directory of only official servers from the companies behind the products, or widely used open source projects, so you can trust the servers you use.

How it works

It's a carefully maintained list, organized into categories such as Cloud and DevOps, Databases, Observability, Browser Automation, Search, Developer Tools, Security, and more. Each entry links to the official repository or official documentation of the server. The project tracks over 389 servers and includes update badges and an awesome-list badge. A table of contents helps you jump to relevant sections.

Who it’s for

Developers and teams building AI assistants that need to connect their AI models to external services via MCP. It's also for anyone who wants to find trustworthy, official MCP servers without scouring the internet, ensuring the tools they integrate are maintained and safe.

Highlights

  • Curated list of official MCP servers only – no unofficial forks or abandoned projects.
  • Over 389 servers listed, covering cloud, databases, observability, browsing, search, and more.
  • Each entry links to the official repository or documentation.
  • Organized by categories with a clickable table of contents for easy navigation.
  • Regular updates and community support via Discord.

Related

  • Project
    ThinkfleetAI/memmesh

    A persistent, local-first memory store for AI agents that provides durable, typed, and searchable memory using a single Rust binary without requiring a hosted vector database.

  • Project
    Gen-Verse/ScienceBuddy

    An interactive scientific agent and workspace that helps researchers analyze papers and data using a recursive self-improvement framework to refine its analysis procedures and models.

  • Project
    kunchenguid/gsh

    A POSIX-compatible generative shell that integrates AI agents directly into the command line for natural language command generation and agentic scripting.

  • Project
    AmrDab/clawdcursor

    Clawd Cursor is a local MCP server that lets AI agents safely control any desktop app. It builds a UI map from the OS accessibility tree + OCR, assigns stable element IDs, and lets agents act by ID instead of pixels. Actions are routed through a single safety gate and verified, with vision used only as a last‑resort fallback. Cross‑OS, npm‑installable, and integrates with Claude Desktop, Cursor, VS Code, Zed, OpenAI Codex, etc.