Magg: The MCP Aggregator Details
Magg is an MCP Aggregator – a meta-MCP server that manages, aggregates, and proxies multiple MCP servers. It acts as a central hub for discovering, configuring, and orchestrating MCP servers, allowing large language models to extend their capabilities at runtime. Magg exposes a suite of tools to search, add, configure, enable/disable, and proxy MCP servers and their tools, merging them under unified prefixes and persisting configurations across sessions. It also includes built-in health and status tools, Real-time Notifications, and MBro (MCP Browser) for interactive exploration, making it easier to compose, manage, and monitor complex MCP ecosystems. Whether you’re running stdio, HTTP, or hybrid transports, Magg provides flexible deployment modes, kit management, and secure access with optional JWT-based authentication.
Use Case
Magg serves as a central MCP registry and proxy layer that lets LLMs dynamically discover, configure, and aggregate MCP servers and their tools. Use Magg to: 1) search for MCP servers and fetch setup instructions; 2) add and configure new MCP servers with per-server prefixes; 3) enable/disable servers on demand; 4) aggregate tools from several servers under a unified namespace; 5) reload configuration from disk and manage kits of servers. The documentation includes concrete usage patterns such as running Magg in different transports, interacting with MBro for exploration, and using Magg’s tools via MCP clients. Example: run Magg in hybrid mode and connect with Claude Code or mbro, then list servers or tools via the MCP interface. See code samples below for authenticating and listing tools with MaggClient or FastMCP Client, and for adding a server via Claude Desktop integration.
Available Tools (16)
Examples & Tutorials
Running Magg and getting started:
<h1 class="text-2xl font-semibold mt-5 mb-3">Install Magg as a tool</h1>
uv tool install magg<h1 class="text-2xl font-semibold mt-5 mb-3">Run with stdio transport (Claude Desktop, Cline, etc.)</h1>
magg serve
<h1 class="text-2xl font-semibold mt-5 mb-3">Run with HTTP transport (system-wide access)</h1>
magg serve --http
Alternative: Run directly from GitHub
<h1 class="text-2xl font-semibold mt-5 mb-3">Run with stdio transport</h1>
uvx --from git+https://github.com/sitbon/magg.git magg<h1 class="text-2xl font-semibold mt-5 mb-3">Run with HTTP transport</h1>
uvx --from git+https://github.com/sitbon/magg.git magg serve --http
Local development:
<h1 class="text-2xl font-semibold mt-5 mb-3">Clone the repository</h1>
git clone https://github.com/sitbon/magg.git
cd magg<h1 class="text-2xl font-semibold mt-5 mb-3">Install in development mode with dev dependencies</h1>
uv sync --dev
<h1 class="text-2xl font-semibold mt-5 mb-3">or with poetry</h1>
poetry install --with dev
<h1 class="text-2xl font-semibold mt-5 mb-3">Run the CLI</h1>
magg --help
Claude Desktop / mbro integration examples:
<h1 class="text-2xl font-semibold mt-5 mb-3">Claude Code example to use Magg in hybrid mode</h1>
claude mcp add magg -- magg serve --hybrid --port 42000MBro usage to inspect Magg:
mbro connect magg "magg serve --hybrid --port 8080"
mbro:local-magg> call magg_status
mbro:local-magg> call magg_list_serversMagg client usage (authenticated via JWT):
from magg.client import MaggClientasync def main():
async with MaggClient("http://localhost:8000/mcp") as client:
tools = await client.list_tools()
JWT authentication with FastMCP:
from fastmcp import Client
from fastmcp.client import BearerAuthjwt_token = "your-jwt-token-here"
async with Client("http://localhost:8000/mcp", auth=BearerAuth(jwt_token)) as client:
tools = await client.list_tools()
Installation Guide
Step-by-step installation and setup from the documentation:
1) Quick Install (Recommended):
<h1 class="text-2xl font-semibold mt-5 mb-3">Install Magg as a tool</h1>
uv tool install magg<h1 class="text-2xl font-semibold mt-5 mb-3">Run with stdio transport</h1>
magg serve
<h1 class="text-2xl font-semibold mt-5 mb-3">Run with HTTP transport</h1>
magg serve --http
2) Alternative: Run Directly from GitHub
<h1 class="text-2xl font-semibold mt-5 mb-3">Run with stdio transport</h1>
uvx --from git+https://github.com/sitbon/magg.git magg<h1 class="text-2xl font-semibold mt-5 mb-3">Run with HTTP transport</h1>
uvx --from git+https://github.com/sitbon/magg.git magg serve --http
3) Local Development:
<h1 class="text-2xl font-semibold mt-5 mb-3">Clone the repository</h1>
git clone https://github.com/sitbon/magg.git
cd magg<h1 class="text-2xl font-semibold mt-5 mb-3">Install in development mode with dev dependencies</h1>
uv sync --dev
<h1 class="text-2xl font-semibold mt-5 mb-3">Or with poetry</h1>
poetry install --with dev
<h1 class="text-2xl font-semibold mt-5 mb-3">Run the CLI</h1>
magg --help
Integration Guides
Frequently Asked Questions
Is this your MCP?
Claim ownership and get verified badge
Notes and important details from the docs:
Prerequisites: Python 3.12 or higher (3.13+ recommended); Python package uv is recommended and can be installed from astral.sh/uv. Magg is run as a tool via uv (uv tool install magg).
Compare Alternatives
Similar MCP Tools
6 related toolsAnki MCP Server
A Model Context Protocol (MCP) server that enables AI assistants to interact with Anki, the spaced repetition flashcard application. The Anki MCP Server allows AI models to access Anki's card data, enabling features like automated flashcard creation, review, and management.
1MCP Agent
A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one. The 1mcp-app/agent is an open-source project that provides a single entry point for multiple MCP servers, making it easier to manage and interact with various AI models and tools.
Roundtable AI MCP Server
Roundtable AI MCP Server is a zero-configuration local MCP server that unifies multiple AI coding assistants (Codex, Claude Code, Cursor, Gemini) through intelligent auto-discovery and a standardized interface. It coordinates specialized sub-agents from within your IDE to solve engineering problems in parallel, sharing context and synthesizing responses into a single, high-quality output. This documentation details installation, available MCP tools, integration with popular IDEs, and a broad ecosystem of specialized tools and CLIs that can be invoked as part of a roundtable-powered workflow, enabling developers to delegate tasks to the right AI for each facet of a problem without leaving their development environment.
MCPJungle
MCPJungle is a self-hosted MCP Gateway and Registry for AI agents. It serves as a central registry and gateway to manage Model Context Protocol (MCP) servers and the tools they expose. By consolidating MCP server registration, tool discovery, and access control, MCPJungle enables AI agents and clients to discover, group, and securely invoke tools from a single, unified gateway. The project provides a CLI, Docker-based deployment options, and enterprise-ready features such as tool grouping, access control, and observability to streamline MCP-based workflows across organizations.
mcpmcp-server
mcpmcp-server is a focused solution for discovering, setting up, and integrating MCP servers with your favorite clients to unlock AI-powered workflows. It streamlines how you connect MCP-powered servers to popular clients, enabling seamless AI-assisted interactions across your daily tools. The project emphasizes an approachable, config-driven approach to linking MCP servers with clients like Claude Desktop, while directing you to the homepage for variations across apps and platforms. This README highlights a practical JSON configuration example and notes on supported environments, helping you get started quickly and confidently.
Imagen3-MCP
Imagen3-MCP is an image generation service based on Google's Imagen 3.0 that exposes its functionality through MCP (Model Control Protocol). The project provides a server to run a local MCP service that accesses Google Gemini-powered image generation, enabling developers to integrate advanced image synthesis into their applications. The documentation covers prerequisites (Gemini API key), installation steps for Cherry Studio, and a Cursor-based JSON configuration example for embedding the MCP server in broader tooling. This MCP is designed to be deployment-friendly, with configurable environment variables and optional proxy settings to adapt to various network environments.