io.github.OnticX/open-mcp-registry
OfficialClick on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@io.github.OnticX/open-mcp-registryfind a server to interact with GitHub"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Open MCP Registry
The MCP registry provides MCP clients with a list of MCP servers, like an app store for MCP servers.
π€ Publish my MCP server | β‘οΈ Live API docs | π Ecosystem vision | π Full documentation
Open MCP Registry is a native Model Context Protocol (MCP) server that allows your AI agents (like Claude Desktop) to programmatically search, discover, and install other MCP servers.
2025-10-24 update: The Registry API has entered an API freeze (v0.1) π. 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 patienceβyour involvement has been key to getting us here!
2025-09-08 update: The registry has launched in preview π (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).
Current key maintainers:
Adam Jones (Anthropic) @domdomegg
Tadas Antanavicius (PulseMCP) @tadasant
Toby Padilla (GitHub) @toby
Radoslav (Rado) Dimitrov (Stacklok) @rdimitrov
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 1.24.x
ko - Container image builder for Go (installation instructions)
golangci-lint v2.4.0
Running the server
# Start full development environment
make dev-composeThis 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.
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-abc123dAvailable tags:
Releases:
latest,v1.0.0,v1.1.0, etc.Continuous:
main(latest main branch build)Development:
main-<date>-<sha>(specific commit builds)
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 --helpSee the publisher guide for more details.
Other commands
# Run lint, unit tests and integration tests
make checkThere are also a few more helpful commands for development. Run make help to learn more, or look in Makefile.
Related MCP server: MCP Registry Server
Architecture
Project Structure
βββ cmd/ # Application entry points
β βββ publisher/ # Server publishing tool
βββ data/ # Seed data
βββ deploy/ # Deployment configuration (Pulumi)
βββ docs/ # Documentation
βββ internal/ # Private application code
β βββ api/ # HTTP handlers and routing
β βββ auth/ # Authentication (GitHub OAuth, JWT, namespace blocking)
β βββ config/ # Configuration management
β βββ database/ # Data persistence (PostgreSQL)
β βββ service/ # Business logic
β βββ telemetry/ # Metrics and monitoring
β βββ validators/ # Input validation
βββ pkg/ # Public packages
β βββ api/ # API types and structures
β β βββ v0/ # Version 0 API types
β βββ model/ # Data models for server.json
βββ scripts/ # Development and testing scripts
βββ tests/ # Integration tests
βββ tools/ # CLI tools and utilities
βββ validate-*.sh # Schema validation toolsAuthentication
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-mcpyou must login to GitHub asdomdomegg, or be in a GitHub Action on domdomegg's reposme.adamjones/my-cool-mcpyou must prove ownership ofadamjones.mevia 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!
Available Tools
1 toolopen_mcp_registryA
Search the MCP Tool Registry for available servers and tools.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max number of results to return. Default 10. | |
| query | No | Keyword search across repository name and description. E.g. 'postgres' or 'weather'. | |
| language | No | Optional programming language to filter by. E.g. 'Python', 'TypeScript', 'Go'. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. The verb 'Search' suggests a read-only operation, but the description does not explicitly state whether this is safe or read-only, nor does it mention return format, pagination, or limitations. It is not misleading but adds minimal behavioral context beyond the obvious.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that immediately front-loads the core purpose. It avoids redundancy and any unnecessary details, making it highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple search tool with optional parameters and no output schema, the description is minimally adequate. It states what the tool does but does not describe the return value shape or any caveats. Given no annotations and no output schema, a bit more detail about results would be helpful, but it is not severely incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides 100% coverage with detailed descriptions for all three parameters (limit, query, language). The tool description does not add any parameter-specific information beyond what the schema already documents, so the baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Search the MCP Tool Registry for available servers and tools.' It uses a specific verb ('Search') and a well-defined resource ('MCP Tool Registry'), leaving no ambiguity about its purpose. Since there are no sibling tools, differentiation is not required.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for locating MCP servers and tools, which is a clear context for use. With no sibling tools or alternative approaches mentioned, there is no need for exclusions. However, it does not explicitly state when to use this tool versus other search mechanisms, but the purpose is straightforward.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
v0.1.0- First observed
open_mcp_registry
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of ambiguity or overlap. The purpose is clear and singular.
With a single tool named 'open_mcp_registry', the naming follows a consistent snake_case style. There is no mixed convention to cause inconsistency.
The server has only one tool, which feels thin for a registry service. While a search tool is core, one tool borders on minimalism and could benefit from additional operations like listing or metadata retrieval.
The tool provides search functionality over the MCP registry, which covers the primary need. Minor gaps exist, such as no direct retrieval by name or browsing capabilities, but the core search use case is addressed.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Publish and discover MCP servers via the official MCP Registry. Powered by HAPI MCP server.
Registry of MCP servers, agent skills and plugins: search, filter, comments, likes, publish.
Registry of MCP servers, agent skills and plugins: search, filter, comments, likes, publish.
Search the official MCP registry: 17,000+ servers with trust grades, stars, tools, install config.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables searching and retrieving detailed information about MCP servers from the official MCP registry. Provides tools to list servers with filtering options and get comprehensive details about specific servers.373MIT
- AlicenseBqualityDmaintenanceEnables discovery and search of available MCP servers through the official MCP Registry. Supports browsing servers with pagination and filtering to find the right MCP tools for your needs.1504MIT
- AlicenseNot gradedqualityBmaintenanceAI-first MCP server discovery tool that enables agents to search, inspect, and install MCP servers from multiple registries.12AGPL 3.0
- AlicenseAqualityDmaintenanceA Model Context Protocol (MCP) server that provides tools to query the official MCP Registry.4523MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/OnticX/open-mcp-registry'
If you have feedback or need assistance with the MCP directory API, please join our Discord server