by metatool-ai
MetaMCP centralizes AI services for secure API key management and unified access, simplifying interactions across multip
Centralizes management of multiple AI services, providing secure API key handling and unified access for streamlined interactions across diverse platforms.
MetaMCP is a community-built MCP server published by metatool-ai that provides AI assistants with tools and capabilities via the Model Context Protocol. MetaMCP centralizes AI services for secure API key management and unified access, simplifying interactions across multip It is categorized under productivity, developer tools.
You can install MetaMCP in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
Apache-2.0
MetaMCP is released under the Apache-2.0 license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
We evaluated MetaMCP against two servers with overlapping tools; this profile had the clearer scope statement.
Useful MCP listing: MetaMCP is the kind of server we cite when onboarding engineers to host + tool permissions.
I recommend MetaMCP for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
MetaMCP is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
MetaMCP is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
MetaMCP is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
MetaMCP reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
MetaMCP is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
Strong directory entry: MetaMCP surfaces stars and publisher context so we could sanity-check maintenance before adopting.
According to our notes, MetaMCP benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
showing 1-10 of 31
🚨 DEPRECATED PACKAGE WARNING 🚨
This local proxy package is deprecated in MetaMCP's 2.0 all-in-one architecture.
Please checkout https://github.com/metatool-ai/metamcp for more details.
MetaMCP MCP Server is a proxy server that joins multiple MCP servers into one. It fetches tool/prompt/resource configurations from MetaMCP App and routes tool/prompt/resource requests to the correct underlying server.
MetaMCP App repo: https://github.com/metatool-ai/metatool-app
Sometimes Smithery works (confirmed in Windsurf locally) but sometimes it is unstable because MetaMCP is special that it runs other MCPs on top of it. Please consider using manual installation if it doesn't work instead.
To install MetaMCP MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @metatool-ai/mcp-server-metamcp --client claude
export METAMCP_API_KEY=<env>
npx -y @metamcp/mcp-server-metamcp@latest
{
"mcpServers": {
"MetaMCP": {
"command": "npx",
"args": ["-y", "@metamcp/mcp-server-metamcp@latest"],
"env": {
"METAMCP_API_KEY": "<your api key>"
}
}
}
}
mcp-server-metamcp --metamcp-api-key <your-api-key>
mcp-server-metamcp --metamcp-api-key <your-api-key> --transport sse --port 12006
With the SSE transport option, the server will start an Express.js web server that listens for SSE connections on the /sse endpoint and accepts messages on the /messages endpoint.
mcp-server-metamcp --metamcp-api-key <your-api-key> --transport streamable-http --port 12006
With the Streamable HTTP transport option, the server will start an Express.js web server that handles HTTP requests. You can optionally use --stateless mode for stateless operation.
When running the server inside a Docker container and connecting to services on the host machine, use the --use-docker-host option to automatically transform localhost URLs:
mcp-server-metamcp --metamcp-api-key <your-api-key> --transport sse --port 12006 --use-docker-host
This will transform any localhost or 127.0.0.1 URLs to host.docker.internal, allowing the container to properly connect to services running on the host.
For STDIO transport, you can control how stderr is handled from child MCP processes:
# Use inherit to see stderr output from child processes
mcp-server-metamcp --metamcp-api-key <your-api-key> --stderr inherit
# Use pipe to capture stderr (default is ignore)
mcp-server-metamcp --metamcp-api-key <your-api-key> --stderr pipe
# Or set via environment variable
METAMCP_STDERR=inherit mcp-server-metamcp --metamcp-api-key <your-api-key>
Available stderr options:
ignore (default): Ignore stderr output from child processesinherit: Pass through stderr from child processes to the parentpipe: Capture stderr in a pipe for processingoverlapped: Use overlapped I/O (Windows-specific)Options:
--metamcp-api-key <key> API key for MetaMCP (can also be set via METAMCP_API_KEY env var)
--metamcp-api-base-url <url> Base URL for MetaMCP API (can also be set via METAMCP_API_BASE_URL env var)
--report Fetch all MCPs, initialize clients, and report tools to MetaMCP API
--transport <type> Transport type to use (stdio, sse, or streamable-http) (default: "stdio")
--port <port> Port to use for SSE or Streamable HTTP transport, defaults to 12006 (default: "12006")
--require-api-auth Require API key in SSE or Streamable HTTP URL path
--stateless Use stateless mode for Streamable HTTP transport
--use-docker-host Transform localhost URLs to use host.docker.internal (can also be set via USE_DOCKER_HOST env var)
--stderr <type> Stderr handling for STDIO transport (overlapped, pipe, ignore, inherit) (default: "ignore")
-h, --help display help for command
METAMCP_API_KEY: API key for MetaMCPMETAMCP_API_BASE_URL: Base URL for MetaMCP APIUSE_DOCKER_HOST: When set to "true", transforms localhost URLs to host.docker.internal for Docker compatibilityMETAMCP_STDERR: Stderr handling for STDIO transport (overlapped, pipe, ignore, inherit). Defaults to "ignore"# Install dependencies
npm install
# Build the application
npm run build
# Watch for changes
npm run watch
sequenceDiagram
participant MCPClient as MCP Client (e.g. Claude Desktop)
participant MetaMCP-mcp-server as MetaMCP MCP Server
participant MetaMCPApp as MetaMCP App
participant MCPServers as Installed MCP Servers in Metatool App
MCPClient ->> MetaMCP-mcp-server: Request list tools
MetaMCP-mcp-server ->> MetaMCPApp: Get tools configuration & status
MetaMCPApp ->> MetaMCP-mcp-server: Return tools configuration & status
loop For each listed MCP Server
MetaMCP-mcp-server ->> MCPServers: Request list_tools
MCPServers ->> MetaMCP-mcp-server: Return list of tools
end
MetaMCP-mcp-server ->> MetaMCP-mcp-server: Aggregate tool lists
MetaMCP-mcp-server ->> MCPClient: Return aggregated list of tools
MCPClient ->> MetaMCP-mcp-server: Call tool
MetaMCP-mcp-server ->> MCPServers: call_tool to target MCP Server
MCPServers ->> MetaMCP-mcp-server: Return tool response
MetaMCP-mcp-server ->> MCPClient: Return tool response
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.