MAGG

v1.0.0Coding Agentsstable

🍎 🪟 🐧 ☁️ 🏠 🐍 - Magg: A meta-MCP server that acts as a universal hub, allowing LLMs to autonomously discover, install, and orchestrate multiple MCP servers - essentially giving AI assistants the power to extend their own capabilities on-demand.

aggregatoraidockerdocker-composefastmcp
Share:
133
Stars
0
Downloads
0
Weekly
0/5

What is MAGG?

MAGG is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🍎 🪟 🐧 ☁️ 🏠 🐍 - magg: a meta-mcp server that acts as a universal hub, allowing llms to autonomously discover, install, and orchestrate multiple mcp servers - essentially giving ai assistants the p...

🍎 🪟 🐧 ☁️ 🏠 🐍 - Magg: A meta-MCP server that acts as a universal hub, allowing LLMs to autonomously discover, install, and orchestrate multiple MCP servers - essentially giving AI assistants the power to extend their own capabilities on-demand.

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • 🍎 🪟 🐧 ☁️ 🏠 🐍 - Magg: A meta-MCP server that acts as a univer

Use Cases

Autonomously discover and install MCP servers
Orchestrate multiple MCP servers together
Extend AI capabilities on-demand
sitbon

Maintainer

LicenseAGPL 3.0
Languagepython
Versionv1.0.0
UpdatedMay 14, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y magg

Manual Installation

npx -y magg

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MAGG

Magg (MCP Aggregator) is a meta-MCP server written in Python that acts as a universal hub, letting LLMs autonomously discover, install, configure, and orchestrate multiple MCP servers at runtime without human intervention. It exposes tools like magg_search, magg_add, magg_enable, and magg_status so AI assistants can extend their own capabilities on demand — effectively functioning as a package manager for LLM tools. Configurations persist in .magg/config.json across sessions, and Magg supports stdio, HTTP, and Docker transports, making it suitable for both local development and production deployments.

Prerequisites

  • Python 3.12 or higher (3.13+ recommended)
  • uv package manager installed from astral.sh/uv
  • An MCP client such as Claude Desktop, Cline, or Cursor
  • Optional: Docker for containerized HTTP transport deployments
  • Optional: RSA key pair for JWT bearer token authentication on HTTP transport
1

Install Magg via uv

Install Magg as a globally available tool using uv tool install. This is the recommended approach as it isolates the environment and makes the magg CLI available system-wide.

uv tool install magg
2

Start the Magg server in stdio mode

Run magg serve to start the server using stdio transport, which is compatible with Claude Desktop, Cline, Cursor, and most MCP clients. For system-wide HTTP access, use the --http flag instead.

# stdio transport (for MCP clients)
magg serve

# HTTP transport (system-wide access on port 8000)
magg serve --http
3

Add the MCP server to your Claude Desktop config

Register Magg in your Claude Desktop (or other client) MCP configuration. Magg runs as a subprocess via stdio, so you point the command at the installed magg binary.

4

Let the LLM discover and add MCP servers

Once connected, your AI assistant can use Magg's built-in tools to search for new MCP servers, add them by URL or registry name, and enable them. Configurations are persisted in .magg/config.json.

5

Check server health and manage kits

Use magg_status to see which servers are running and healthy. Bundle related servers into kits with magg_kit_create for easy group loading and unloading.

# Check all server health via the CLI browser
uvx --from magg mbro

# Or run directly from GitHub without installing
uvx --from git+https://github.com/sitbon/magg.git magg serve

MAGG Examples

Client configuration

Add Magg to Claude Desktop's MCP configuration. Magg will then expose tools that let the AI assistant discover and add more MCP servers dynamically.

{
  "mcpServers": {
    "magg": {
      "command": "magg",
      "args": ["serve"]
    }
  }
}

Prompts to try

Once Magg is running, your AI assistant can manage its own tool ecosystem through these kinds of requests.

- "Search for an MCP server that can browse the web and add it"
- "List all MCP servers currently managed by Magg and their status"
- "Enable the filesystem MCP server so I can read local files"
- "Create a kit called 'research' with the web search and arxiv servers"
- "Check the health of all connected MCP servers"

Troubleshooting MAGG

magg command not found after installation

Ensure uv's tool bin directory is in your PATH. Run uv tool dir to find the location, then add it to your shell profile (e.g., export PATH="$HOME/.local/bin:$PATH").

Dynamic tool updates not appearing in Claude Desktop

Claude Desktop does not support MCP notifications for dynamic tool updates. Use the ProxyMCP tool that Magg includes specifically for clients lacking notification support — it proxies the protocol to itself to surface updated tools.

Authentication errors on HTTP transport

When running magg serve --http with authentication enabled, you must provide an RSA private key. Set the MAGG_PRIVATE_KEY environment variable with the key content, or mount ~/.ssh/magg/magg.key when using Docker.

Frequently Asked Questions about MAGG

What is MAGG?

MAGG is a Model Context Protocol (MCP) server that 🍎 🪟 🐧 ☁️ 🏠 🐍 - magg: a meta-mcp server that acts as a universal hub, allowing llms to autonomously discover, install, and orchestrate multiple mcp servers - essentially giving ai assistants the power to extend their own capabilities on-demand. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MAGG?

Install via npm with the command: npx -y magg. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with MAGG?

MAGG works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MAGG free to use?

Yes, MAGG is open source and available under the AGPL 3.0 license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "magg": { "command": "npx", "args": ["-y", "magg"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use MAGG?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides