A Model Context Protocol server that manages, aggregates, and proxies other MCP servers, enabling LLMs to dynamically extend their own capabilities.
Magg is a meta-MCP server that acts as a central hub for managing multiple MCP servers. It provides tools that allow LLMs to:
- Search for new MCP servers and discover setup instructions
- Add and configure MCP servers dynamically
- Enable/disable servers on demand
- Aggregate tools from multiple servers under unified prefixes
- Persist configurations across sessions
Think of Magg as a "package manager for LLM tools" - it lets AI assistants install and manage their own capabilities at runtime.
- Self-Service Tool Management: LLMs can search for and add new MCP servers without human intervention.
- Dynamic Configuration Reloading: Automatically detects and applies config changes without restarting.
- Automatic Tool Proxying: Tools from added servers are automatically exposed with configurable prefixes.
- ProxyMCP Tool: A built-in tool that proxies the MCP protocol to itself, for clients that don't support notifications or dynamic tool updates (which is most of them currently).
- Smart Configuration: Uses MCP sampling to intelligently configure servers from just a URL.
- Persistent Configuration: Maintains server configurations in
.magg/config.json. - Multiple Transport Support: Works with stdio, HTTP, and in-memory transports.
- Bearer Token Authentication: Optional RSA-based JWT authentication for secure HTTP access.
- Docker Support: Pre-built images for production, staging, and development workflows.
- Health Monitoring: Built-in
magg_statusandmagg_checktools for server health checks. - Real-time Messaging: Full support for MCP notifications and messages - receive tool/resource updates and progress notifications from backend servers.
- Python 3.12+ Support: Fully compatible with Python 3.12 and 3.13.
- Kit Management: Bundle related MCP servers into kits for easy loading/unloading as a group.
- MBro CLI: Included MCP Browser for interactive exploration and management of MCP servers, with script support for automation.
- Python 3.12 or higher (3.13+ recommended)
uv(recommended) - Install from astral.sh/uv
The easiest way to install Magg is as a tool using uv:
# Install Magg as a tool
uv tool install magg
# Run with stdio transport (for Claude Desktop, Cline, etc.)
magg serve
# Run with HTTP transport (for system-wide access)
magg serve --httpYou can also run Magg directly from GitHub without installing:
# Run with stdio transport
uvx --from git+https://github.com/sitbon/magg.git magg
# Run with HTTP transport
uvx --from git+https://github.com/sitbon/magg.git magg serve --httpFor development, clone the repository and install in editable mode:
# Clone the repository
git clone https://github.com/sitbon/magg.git
cd magg
# Install in development mode with dev dependencies
uv sync --dev
# Or with poetry
poetry install --with dev
# Run the CLI
magg --helpMagg is available as pre-built Docker images from GitHub Container Registry:
# Run production image (WARNING log level)
docker run -p 8000:8000 ghcr.io/sitbon/magg:latest
# Run with authentication (mount or set private key)
docker run -p 8000:8000 \
-v ~/.ssh/magg:/home/magg/.ssh/magg:ro \
ghcr.io/sitbon/magg:latest
# Or with environment variable
docker run -p 8000:8000 \
-e MAGG_PRIVATE_KEY="$(cat ~/.ssh/magg/magg.key)" \
ghcr.io/sitbon/magg:latest
# Run beta image (INFO log level)
docker run -p 8000:8000 ghcr.io/sitbon/magg:beta
# Run with custom config directory
docker run -p 8000:8000 \
-v /path/to/config:/home/magg/.magg \
ghcr.io/sitbon/magg:latestMagg uses a multi-stage Docker build with three target stages:
pro(Production): Minimal image with WARNING log level, suitable for production deploymentspre(Pre-production): Same as production but with INFO log level for staging/testing (available but not published)dev(Development): Includes development dependencies and DEBUG logging for troubleshooting
Images are automatically published to GitHub Container Registry with the following tags:
- Version tags (from main branch):
1.2.3,1.2,dev,1.2-dev,1.2-dev-py3.12, etc. - Branch tags (from beta branch):
beta,beta-dev - Python-specific dev tags:
beta-dev-py3.12,beta-dev-py3.13, etc.
Pull requests build and test images but do not publish them unless a maintainer adds the
push-image label, which publishes ephemeral pr-NN / pr-NN-dev tags (same-repo PRs
only). Ephemeral pr-* tags and untagged manifests are cleaned up weekly; version tags
are kept forever, so pinned deployments are never affected.
For easier management, use Docker Compose:
# Clone the repository
git clone https://github.com/sitbon/magg.git
cd magg
# Run production version
docker compose up magg
# Run staging version (on port 8001)
docker compose up magg-beta
# Run development version (on port 8008)# This uses ./.magg/config.json for configuration
docker compose up magg-dev
# Build and run with custom registry
REGISTRY=my.registry.com docker compose build
REGISTRY=my.registry.com docker compose pushSee compose.yaml and .env.example for configuration options.
Magg can run in three modes:
Stdio Mode (default) - For integration with Claude Desktop, Cline, Cursor, etc.:
magg serve
HTTP Mode - For system-wide access or web integrations:
magg serve --http --port 8000
Hybrid Mode - Both stdio and HTTP simultaneously:
magg serve --hybrid magg serve --hybrid --port 8080 # Custom portThis is particularly useful when you want to use Magg through an MCP client while also allowing HTTP access. For example:
With Claude Code:
# Configure Claude Code to use Magg in hybrid mode claude mcp add magg -- magg serve --hybrid --port 42000With mbro:
# mbro hosts Magg and connects via stdio mbro connect magg "magg serve --hybrid --port 8080"# Other mbro instances can connect via HTTP mbro connect magg http://localhost:8080
Once Magg is running, it exposes the following tools to LLMs:
magg_list_servers- List all configured MCP serversmagg_add_server- Add a new MCP servermagg_remove_server- Remove a servermagg_enable_server/magg_disable_server- Toggle server availabilitymagg_search_servers- Search for MCP servers onlinemagg_list_tools- List all available tools from all serversmagg_smart_configure- Intelligently configure a server from a URLmagg_analyze_servers- Analyze configured servers and suggest improvementsmagg_status- Get server and tool statisticsmagg_check- Health check servers with repair actions (report/remount/unmount/disable)magg_reload_config- Reload configuration from disk and apply changesmagg_load_kit- Load a kit and its servers into the configurationmagg_unload_kit- Unload a kit and optionally its servers from the configurationmagg_list_kits- List all available kits with their statusmagg_kit_info- Get detailed information about a specific kit
Magg includes the mbro (MCP Browser) CLI tool for interactive exploration. A unique feature is the ability to connect to Magg in stdio mode for quick inspection:
# Connect mbro to a Magg instance via stdio (no HTTP server needed)
mbro connect local-magg magg serve
# Now inspect your Magg setup from the MCP client perspective
mbro:local-magg> call magg_status
mbro:local-magg> call magg_list_serversMBro also supports:
- Scripts: Create
.mbrofiles with commands for automation - Shell-style arguments: Use
key=valuesyntax instead of JSON - Tab completion: Rich parameter hints after connecting
See the MBro Documentation for details.
Magg supports optional bearer token authentication to secure access:
Initialize authentication (creates RSA keypair):
magg auth init
Generate a JWT token for clients:
# Generate token (displays on screen) magg auth token # Export as environment variableexport MAGG_JWT=$(magg auth token -q)
Connect with authentication:
- Using
MaggClient(auto-loads from MAGG_JWT):frommagg.clientimportMaggClientasyncdefmain(): asyncwithMaggClient("http://localhost:8000/mcp") asclient: tools=awaitclient.list_tools()
- Using FastMCP with explicit token:
fromfastmcpimportClientfromfastmcp.clientimportBearerAuthjwt_token="your-jwt-token-here"asyncwithClient("http://localhost:8000/mcp", auth=BearerAuth(jwt_token)) asclient: tools=awaitclient.list_tools()
- Using
- Keys are stored in
~/.ssh/magg/by default - Private key can be set via
MAGG_PRIVATE_KEYenvironment variable - To disable auth, remove keys or set non-existent
key_pathin.magg/auth.json
magg auth init- Initialize authentication (generates RSA keypair)magg auth status- Check authentication configurationmagg auth token- Generate JWT tokenmagg auth public-key- Display public key (for verification)magg auth private-key- Display private key (for backup)
See examples/authentication.py for more usage patterns.
Magg stores its configuration in .magg/config.json in your current working directory. This allows for project-specific tool configurations.
Magg supports automatic configuration reloading without requiring a restart:
- Automatic file watching: Detects changes to
config.jsonand reloads automatically (uses watchdog when available) - SIGHUP signal: Send
kill -HUP <pid>to trigger immediate reload (Unix-like systems) - MCP tool: Use
magg_reload_configtool from any MCP client - Smart transitions: Only affected servers are restarted during reload
Configuration reload is enabled by default. You can control it with:
MAGG_AUTO_RELOAD=false- Disable automatic reloadingMAGG_RELOAD_POLL_INTERVAL=5.0- Set polling interval in seconds (when watchdog unavailable)
See Configuration Reload Documentation for detailed information.
Magg supports several environment variables for configuration:
MAGG_CONFIG_PATH- Path to config file (default:.magg/config.json)MAGG_LOG_LEVEL- Logging level: DEBUG, INFO, WARNING, ERROR, CRITICAL (default: INFO)MAGG_STDERR_SHOW=1- Show stderr output from subprocess MCP servers (default: suppressed)MAGG_AUTO_RELOAD- Enable/disable config auto-reload (default: true)MAGG_RELOAD_POLL_INTERVAL- Config polling interval in seconds (default: 1.0)MAGG_READ_ONLY=true- Run in read-only modeMAGG_SELF_PREFIX- Prefix for Magg tools (default: "magg"). Tools will be named as{prefix}{sep}{tool}(e.g.,magg_list_servers)MAGG_PREFIX_SEP- Separator between prefix and tool name (default: "_")
Example configuration:
{
"servers": {
"calculator": {
"name": "calculator",
"source": "https://github.com/executeautomation/calculator-mcp",
"command": "npx @executeautomation/calculator-mcp",
"prefix": "calc",
"enabled": true
}
}
}Servers can be added in several ways:
Using the LLM (recommended):
"Add the Playwright MCP server" "Search for and add a calculator tool"Manual configuration via
magg_add_server:name: playwright url: https://github.com/microsoft/playwright-mcp command: npx @playwright/mcp@latest prefix: pwThe
magg serverCLI (see below)Direct config editing: Edit
.magg/config.jsondirectly
Server and kit configuration can be managed entirely from the command line — no MCP client
or running server required. The CLI edits .magg/config.json directly, and a running Magg
instance picks up the changes automatically via config reload.
(Tools that require a live server, like magg_search_servers, magg_check, and
magg_smart_configure, remain available through any MCP client such as mbro.)
# List servers (human-readable, or JSON on stdout for scripting)
magg server list
magg server list --json
# Add a server
magg server add playwright https://github.com/microsoft/playwright-mcp \
--command "npx @playwright/mcp@latest" --prefix pw
# Add a server without enabling it, with transport options
magg server add web https://example.com/web --uri http://localhost:9000/mcp \
--transport '{"keep_alive": false}' --disable
# Update an existing server (pass '' to clear an optional field)
magg server update playwright --prefix play --notes "Browser automation"
magg server update playwright --command "npx @playwright/mcp@next"
magg server update playwright --notes ""# Enable / disable / inspect / remove
magg server enable playwright
magg server disable playwright
magg server info playwright --json
magg server remove playwrightThe MaggClient now supports real-time notifications from backend MCP servers:
frommaggimportMaggClient, MaggMessageHandler# Using callbackshandler=MaggMessageHandler(
on_tool_list_changed=lambdan: print("Tools changed!"),
on_progress=lambdan: print(f"Progress: {n.params.progress}")
)
asyncwithMaggClient("http://localhost:8000/mcp", message_handler=handler) asclient:
# Client will receive notifications while connectedtools=awaitclient.list_tools()See Messaging Documentation for advanced usage including custom message handlers.
Magg supports organizing related MCP servers into "kits" - bundles that can be loaded and unloaded as a group:
# List available kits
magg kit list
# Load a kit (adds all its servers)
magg kit load web-tools
# Unload a kit (removes servers only in that kit)
magg kit unload web-tools
# Get information about a kit
magg kit info web-tools
# Export the current configuration (or a loaded kit) as a kit file
magg kit export --name my-kit --output my-kit.jsonWhen unloading a kit, servers that belong only to that kit are removed, while servers shared with other kits are kept.
You can also manage kits programmatically through Magg's tools when connected via an MCP client:
magg_list_kits- List all available kitsmagg_load_kit- Load a kit and its serversmagg_unload_kit- Unload a kitmagg_kit_info- Get detailed kit information
Kits are JSON files stored in ~/.magg/kit.d/ or .magg/kit.d/ that define a collection of related servers. See Kit Documentation for details on creating and managing kits.
Automate common workflows with MBro scripts:
# Create a setup script
cat > setup.mbro <<EOF# Connect to Magg and check statusconnect magg magg servecall magg_statuscall magg_list_servers# Add a new server if neededcall magg_add_server name=calculator source="npx -y @modelcontextprotocol/server-calculator"EOF# Run the script
mbro -x setup.mbroThe MCP 2026-07-28 spec moves the protocol to a stateless request/response core. Magg's take: something still has to own long-lived stdio subprocesses, backend connections, and tool-list caching — and that's exactly the layer an aggregator provides. See Magg and the Stateless MCP Spec for the impact analysis and migration plan, including how Magg bridges pre-2026 (stateful) backends to stateless-era clients and how hierarchical Magg deployments fit in.
For more documentation, see docs/.
Magg appears in multiple locations. Please feel free to submit a PR to add more appearances below in alphabetical order.
Magg ships a server.json manifest for the
official MCP Registry (as io.github.sitbon/magg),
and magg_search_servers queries the registry as a first-class discovery source alongside
Glama, GitHub, and npm. See MCP Registry Documentation for publishing
instructions.
mcp-name: io.github.sitbon/magg