Skip to main content
Glama

SuperMCP

SuperMCP is an orchestration layer for Model Context Protocol (MCP) servers. It gives an AI assistant a single entry point to dynamically discover, inspect, and call tools across many MCP servers — without hard-coding anything.

How It Works

SuperMCP starts
  └─ reads SUPERMCP_REGISTRY   (env var, or from .env file)
       └─ points to a registry file anywhere on disk
            └─ loads mcpServers from that file
                 └─ resolves relative paths from the registry's directory

Because the registry file can live anywhere, you can keep your servers and their configuration wherever makes sense — a project folder, a shared drive, a dotfiles repo — and just point SuperMCP at it.

Related MCP server: MCPilot

Quick Start

  1. Clone & install dependencies

git clone https://github.com/YakupAtahanov/SuperMCP.git
cd SuperMCP
uv pip install "mcp[cli]"
  1. Configure the registry path

cp .env.example .env

Edit .env:

SUPERMCP_REGISTRY=C:/Users/you/my-servers/mcp.json

The path can be absolute or relative (relative paths resolve from the SuperMCP directory).

Alternatively, pass it as an environment variable when launching:

SUPERMCP_REGISTRY=/path/to/mcp.json python SuperMCP.py

Or set it in your MCP host (e.g. Cursor):

{
  "command": "python",
  "args": ["C:/path/to/SuperMCP.py"],
  "env": { "SUPERMCP_REGISTRY": "C:/Users/you/my-servers/mcp.json" }
}
  1. Create your registry file at that location:

{
  "mcpServers": {
    "ShellMCP": {
      "command": "python",
      "args": [".mcps/ShellMCP/server.py"],
      "type": "stdio",
      "description": "Shell command execution",
      "enabled": true
    }
  }
}

Relative paths inside the registry (like .mcps/ShellMCP/server.py) resolve from the registry file's directory.

  1. Run

python SuperMCP.py

Available Tools

Tool

Description

reload_servers

Reload the registry and rebuild the in-memory server list

list_servers

List all registered MCP servers

inspect_server

Inspect a server's tools, prompts, and resources

call_server_tool

Call a tool on any registered server

add_server

Add a new server (SSE or stdio) to the registry

remove_server

Remove a server from the registry

update_server

Update a server's configuration

Server Types

Stdio (local process)

{
  "mcpServers": {
    "my-server": {
      "command": "python",
      "args": ["path/to/server.py"],
      "type": "stdio",
      "description": "A local MCP server",
      "enabled": true
    }
  }
}

SSE (remote endpoint)

{
  "mcpServers": {
    "remote-server": {
      "url": "https://example.com/mcp/sse",
      "type": "sse",
      "description": "A remote SSE server",
      "enabled": true,
      "env": {
        "API_KEY": "your-key"
      }
    }
  }
}

Environment variables in the env field are sent as HTTP headers in the format X-MCP-{VAR_NAME}.

Git-based Stdio

{
  "mcpServers": {
    "weather-mcp": {
      "command": "python",
      "args": [".mcps/remote/weather-mcp/server.py"],
      "type": "stdio",
      "url": "https://github.com/user/weather-mcp.git",
      "description": "Cloned from Git, runs locally",
      "enabled": true
    }
  }
}

When a stdio server has a url field, SuperMCP clones the repository into .mcps/remote/<name>/ (relative to the registry) and installs its dependencies.

Project Structure

SuperMCP/
├── SuperMCP.py          # Main orchestration server
├── server_manager.py    # Git cloning, SSE testing, dependency install
├── .env.example         # Template — copy to .env and set SUPERMCP_REGISTRY
├── pyproject.toml       # Python dependencies
├── ARCHITECTURE.md      # Architecture overview
└── README.md

Contributing

Contributions welcome. Whether you're building new MCP servers, improving the orchestration layer, or enhancing documentation — all help is appreciated.

License

See LICENSE.

A
license - permissive license
-
quality - not tested
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • F
    license
    C
    quality
    D
    maintenance
    A powerful gateway for the Model Context Protocol (MCP) that unifies AI toolchains by federating multiple MCP servers, wrapping REST APIs as MCP tools, and supporting multiple transport methods with an admin dashboard.
    1
  • F
    license
    -
    quality
    D
    maintenance
    A centralized management platform that aggregates multiple Model Context Protocol (MCP) servers into a single unified endpoint for AI agents. It provides a web interface for hot-swappable tool management, proxying of existing servers, and AI-powered generation of custom MCP plugins.
    1
  • F
    license
    -
    quality
    B
    maintenance
    A service orchestration layer for the Model Context Protocol. Manages multiple MCP services through a single unified interface — spawn, supervise, and route tool calls across all your services.
    36
    1

View all related MCP servers

Related MCP Connectors

  • A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…

  • MCP Hub: AI service discovery, per-user OAuth, and multi-service workflow orchestration

  • Personal assistant MCP server with search, execute, packages, jobs, secrets, and integrations.

View all MCP Connectors

Latest Blog Posts

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/YakupAtahanov/SuperMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server