Practical overview
When it fits
Use MetaMCP when an MCP client or agent needs a centrally composed set of tools from multiple MCP servers, or when developers want to inspect their configured MetaMCP endpoints.
Who it is for
- Developers building AI applications or agents that need tools from multiple MCP servers.
- Teams that want to manage MCP server groupings and expose selected tools through shared endpoints.
- Developers who need an inspector for saved MCP server configurations and MetaMCP endpoints.
Documented uses
- Combine multiple MCP servers behind one MCP server.
- Group MCP servers into namespaces and assign public endpoints.
- Choose which tools from composed servers are exposed.
- Connect an MCP client to the unified server.
- Save server configurations and inspect MetaMCP endpoints.
Requirements & limits
The repository provides Docker Compose deployment instructions and publishes the project under the MIT license. It describes MetaMCP as self-hostable.
- The project is infrastructure that exposes MCP tools to clients; an AI application or agent is built separately on top of it.
- The README identifies observability and security middleware as coming soon, rather than established current functionality.
- The README recommends at least 2–4 GB of memory for deployment to a VPS or online service.
- The repository's ai-dev branch contains ongoing AI-agent changes and carries a recommendation to test before building an image from it.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Start MetaMCP with Docker Compose
Clone the repository, prepare its environment file, and start the Compose services.
Before you start
- Docker and Docker Compose
- A network connection to retrieve the repository and required container resources
Steps
Clone the MetaMCP repository.
Change into the metamcp directory.
Copy example.env to .env.
Run docker compose up -d.
Expected outcome
The Docker Compose services are started in the background.
Guide limitations
- If APP_URL environment variables are changed, the README says to access MetaMCP only through the configured APP_URL because of its CORS policy.
- The PostgreSQL volume name may collide with other PostgreSQL Docker volumes; the README suggests renaming it in docker-compose.yml.
- The guide does not cover connecting an MCP client or configuring a production deployment.
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 9 October 2026
- Original website title
- metatool-ai/metamcp · Official homepage title · retained in its source language

