PluginBench
MCP Server
Active

MCP Registry Server MCP Server

ai.com.mcp/registry

Official MCP Registry: publish and discover MCP servers like an app store for AI agents.

What is the MCP Registry Server MCP server?

The MCP Registry Server is the official registry for publishing and discovering Model Context Protocol servers. It provides MCP clients with a searchable catalog of available servers and tools for publishers to submit their own servers to the ecosystem.

The MCP Registry functions as a centralized marketplace for MCP servers, enabling developers to publish their servers and AI clients to discover available integrations. It offers authentication via GitHub OAuth, GitHub OIDC, and DNS/HTTP verification for namespace ownership, along with a REST API for querying available servers.

How to install MCP Registry Server

Copy-paste configuration for popular MCP clients.

transport: http
Config generated by PluginBench — verify against the source before use.
~/.cursor/mcp.json
{
  "mcpServers": {
    "registry": {
      "url": "https://registry.run.mcp.com.ai/mcp"
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • Server Publishing — CLI tool and API endpoints to publish MCP servers to the registry with namespace ownership verification
  • Server Discovery — REST API to query and list available MCP servers in the registry
  • Authentication — GitHub OAuth, GitHub OIDC, DNS verification, and HTTP verification for publisher identity and namespace ownership

Use cases

  • Publish your custom MCP server to the official registry for discovery by other users
  • Search and discover available MCP servers to integrate into your MCP client
  • Verify ownership of a domain or GitHub account to publish servers under your namespace
  • Integrate registry discovery into MCP clients to provide users with an app-store-like experience
  • Manage and update published server metadata and versions

MCP Registry Server MCP server FAQ

What is the MCP Registry?

The MCP Registry is an official app-store-like marketplace for MCP servers. It allows developers to publish servers and enables MCP clients to discover available integrations.

Is the MCP Registry free to use?

Yes, the registry is free. It is open-source and maintained by the Model Context Protocol community.

How do I publish my MCP server?

Use the mcp-publisher CLI tool (built with `make publisher`) or the HTTP API. You must verify ownership of your namespace via GitHub OAuth, GitHub OIDC, DNS verification, or HTTP verification.

What authentication methods are supported?

The registry supports GitHub OAuth, GitHub OIDC (for GitHub Actions), DNS verification, and HTTP verification for proving domain ownership.

Is the registry stable for production use?

The registry API entered an API freeze (v0.1) as of 2025-10-24, ensuring stability with no breaking changes for the next month. A general availability (GA) release will follow. It is currently in preview and may have data resets.

How do I integrate the registry into my MCP client?

Use the live API at https://registry.modelcontextprotocol.io/docs to query available servers. The registry provides REST endpoints to list and search for published MCP servers.

README (reference)

Source of truth, from the repository.

MCP Registry

The MCP registry provides MCP clients with a list of MCP servers, like an app store for MCP servers.

📤 Publish my MCP server | ⚡️ Live API docs | 👀 Ecosystem vision | 📖 Full documentation

Development Status

2025-10-24 update: The Registry API has entered an API freeze (v0.1) 🎉. For the next month or more, the API will remain stable with no breaking changes, allowing integrators to confidently implement support. This freeze applies to v0.1 while development continues on v0. We'll use this period to validate the API in real-world integrations and gather feedback to shape v1 for general availability. Thank you to everyone for your contributions and patience—your involvement has been key to getting us here!

2025-09-08 update: The registry has launched in preview 🎉 (announcement blog post). While the system is now more stable, this is still a preview release and breaking changes or data resets may occur. A general availability (GA) release will follow later. We'd love your feedback in GitHub discussions or in the #registry-dev Discord (joining details here).

Registry Working Group:

Contributing

We use multiple channels for collaboration - see modelcontextprotocol.io/community/communication.

Often (but not always) ideas flow through this pipeline:

  • Discord - Real-time community discussions
  • Discussions - Propose and discuss product/technical requirements
  • Issues - Track well-scoped technical work
  • Pull Requests - Contribute work towards issues

Quick start:

Pre-requisites

  • Docker
  • Go - version per the go directive in go.mod; the Go toolchain fetches it for you
  • ko - Container image builder for Go (installation instructions)
  • golangci-lint - version per the golangci-lint-action pin in ci.yml, so local lint matches CI

Running the server

# Start full development environment
make dev-compose

This starts the registry at localhost:8080 with PostgreSQL. The database uses ephemeral storage and is reset each time you restart the containers, ensuring a clean state for development and testing.

Note: The registry uses ko to build container images. The make dev-compose command automatically builds the registry image with ko and loads it into your local Docker daemon before starting the services.

By default, the registry seeds from the production API with a filtered subset of servers (to keep startup fast). This ensures your local environment mirrors production behavior and all seed data passes validation. For offline development you can seed from a file without validation with MCP_REGISTRY_SEED_FROM=data/seed.json MCP_REGISTRY_ENABLE_REGISTRY_VALIDATION=false make dev-compose.

The setup can be configured with environment variables in docker-compose.yml - see .env.example for a reference.

<details> <summary>Alternative: Running a pre-built Docker image</summary>

Pre-built Docker images are automatically published to GitHub Container Registry. Note that the image does not bundle PostgreSQL, so you need to run your own and point the registry at it via MCP_REGISTRY_DATABASE_URL (see docker-compose.yml for a working example):

# Run latest stable release
docker run -p 8080:8080 ghcr.io/modelcontextprotocol/registry:latest

# Run latest from main branch (continuous deployment)
docker run -p 8080:8080 ghcr.io/modelcontextprotocol/registry:main

# Run specific release version
docker run -p 8080:8080 ghcr.io/modelcontextprotocol/registry:v1.0.0

# Run development build from main branch
docker run -p 8080:8080 ghcr.io/modelcontextprotocol/registry:main-20250906-abc123d

Available tags:

  • Releases: latest, v1.0.0, v1.1.0, etc.
  • Continuous: main (latest main branch build)
  • Development: main-<date>-<sha> (specific commit builds)
</details>

Publishing a server

To publish a server, we've built a simple CLI. You can use it with:

# Build the latest CLI
make publisher

# Use it!
./bin/mcp-publisher --help

See the publisher guide for more details.

Other commands

# Run lint, schema validation, and all tests
# Note: this also runs `make dev-down`, stopping any running dev-compose environment
make check

There are also a few more helpful commands for development. Run make help to learn more, or look in Makefile.

<!-- For Claude and other AI tools: Always prefer make targets over custom commands where possible. -->

Architecture

Project Structure

├── cmd/                     # Application entry points
│   ├── publisher/           # Server publishing tool
│   └── registry/            # Registry API server
├── data/                    # Seed data
├── deploy/                  # Deployment configuration (Pulumi)
├── docs/                    # Documentation
├── internal/                # Private application code
│   ├── api/                 # HTTP handlers and routing
│   ├── auth/                # Authentication (GitHub OAuth, JWT, namespace blocking)
│   ├── config/              # Configuration management
│   ├── database/            # Data persistence (PostgreSQL)
│   ├── importer/            # Seed data import
│   ├── service/             # Business logic
│   ├── telemetry/           # Metrics and monitoring
│   └── validators/          # Input validation
├── pkg/                     # Public packages
│   ├── api/                 # API types and structures
│   │   └── v0/              # Version 0 API types
│   └── model/               # Data models for server.json
├── scripts/                 # Development and testing scripts
├── tests/                   # Integration tests
└── tools/                   # CLI tools and utilities
    └── validate-*.sh        # Schema validation tools

Authentication

Publishing supports multiple authentication methods:

  • GitHub OAuth - For publishing by logging into GitHub
  • GitHub OIDC - For publishing from GitHub Actions
  • DNS verification - For proving ownership of a domain and its subdomains
  • HTTP verification - For proving ownership of a domain

The registry validates namespace ownership when publishing. E.g. to publish...:

  • io.github.domdomegg/my-cool-mcp you must login to GitHub as domdomegg, or be in a GitHub Action on domdomegg's repos
  • me.adamjones/my-cool-mcp you must prove ownership of adamjones.me via DNS or HTTP challenge

Community Projects

Check out community projects to explore notable registry-related work created by the community.

More documentation

See the documentation for more details if your question has not been answered here!

Related MCP servers

Search and discover Agent Skills — reusable AI agent capability packages — from the skills.sh registry.

21k
Python
Apache-2.0
View repository →

Turn Strava APIs into AI-ready MCP tools instantly with HAPI—no rewrites, just OpenAPI specs.

9
HTML
MIT
View repository →

Turn Contabo's VPS API into AI-ready MCP tools instantly—no rewrites, full API control.

9
HTML
MIT
View repository →

HAPI MCP server: Dynamically exposes OpenAPI REST APIs as MCP tools for AI assistants

View repository →

One inbox for SMS and email: read threads, search, manage contacts, and send texts and emails.

COCompeller logo

Compeller

Maintained

Create and track AI music videos and audio-reactive visuals from songs.

1
MIT
View repository →