FastMCP provides a command-line interface (CLI) that makes it easy to run, develop, and install your MCP servers. The CLI is automatically installed when you install FastMCP.

fastmcp --help

​
Commands Overview

CommandPurposeDependency Management
runRun a FastMCP server directlyUses your current environment; you are responsible for ensuring all dependencies are available
devRun a server with the MCP Inspector for testingCreates an isolated environment; dependencies must be explicitly specified with --with and/or --with-editable
installInstall a server in the Claude desktop appCreates an isolated environment; dependencies must be explicitly specified with --with and/or --with-editable
versionDisplay version informationN/A

​
Command Details

​
run

Run a FastMCP server directly.

fastmcp run server.py

This command runs the server directly in your current Python environment. You are responsible for ensuring all dependencies are available.

​
Options

OptionFlagDescription
Transport--transport, -tTransport protocol to use (stdio, streamable-http, or sse)
Host--hostHost to bind to when using http transport (default: 127.0.0.1)
Port--port, -pPort to bind to when using http transport (default: 8000)
Log Level--log-level, -lLog level (DEBUG, INFO, WARNING, ERROR, CRITICAL)

​
Server Specification

The server can be specified in two ways:

  1. server.py - imports the module and looks for a FastMCP object named mcp, server, or app. Errors if no such object is found.
  2. server.py:custom_name - imports and uses the specified server object

When using fastmcp run, it ignores the if __name__ == "__main__" block entirely. Instead, it finds your server object and calls its run() method directly with the transport options you specify. This means you can use fastmcp run to override the transport specified in your code.

For example, if your code contains:

# server.py
from fastmcp import FastMCP

mcp = FastMCP("MyServer")

@mcp.tool()
def hello(name: str) -> str:
    return f"Hello, {name}!"

if __name__ == "__main__":
    # This is ignored when using `fastmcp run`!
    mcp.run(transport="stdio")

You can run it with Streamable HTTP transport regardless of what’s in the __main__ block:

fastmcp run server.py --transport streamable-http --port 8000

Example

# Run a server with Streamable HTTP transport on a custom port
fastmcp run server.py --transport streamable-http --port 8000

​
dev

Run a MCP server with the MCP Inspector for testing.

fastmcp dev server.py

This command runs your server in an isolated environment. All dependencies must be explicitly specified using the --with and/or --with-editable options.

The dev command is a shortcut for testing a server over STDIO only. When the Inspector launches, you may need to:

  1. Select “STDIO” from the transport dropdown
  2. Connect manually

This command does not support HTTP testing. To test a server over HTTP:

  1. Start your server manually with HTTP transport using either: 
    fastmcp run server.py --transport streamable-http
    or 
    python server.py  # Assuming your __main__ block sets HTTP transport
  2. Open the MCP Inspector separately and connect to your running server

​
Options

OptionFlagDescription
Editable Package--with-editable, -eDirectory containing pyproject.toml to install in editable mode
Additional Packages--withAdditional packages to install (can be used multiple times)
Inspector Version--inspector-versionVersion of the MCP Inspector to use
UI Port--ui-portPort for the MCP Inspector UI
Server Port--server-portPort for the MCP Inspector Proxy server

Example

# Run dev server with editable mode and additional packages
fastmcp dev server.py -e . --with pandas --with matplotlib

​
install

Install a MCP server in the Claude desktop app.

fastmcp install server.py

This command installs your server in an isolated environment. All dependencies must be explicitly specified using the --with and/or --with-editable options.

The install command currently only sets up servers for STDIO transport. When installed in the Claude desktop app, your server will be run using STDIO regardless of any transport configuration in your code.

​
Options

OptionFlagDescription
Server Name--name, -nCustom name for the server
Editable Package--with-editable, -eDirectory containing pyproject.toml to install in editable mode
Additional Packages--withAdditional packages to install (can be used multiple times)
Environment Variables--env-var, -vEnvironment variables in KEY=VALUE format (can be used multiple times)
Environment File--env-file, -fLoad environment variables from a .env file

Example

# Install server with custom name, dependencies, and environment variables
fastmcp install server.py -n "My Analysis Server" -e . --with pandas --env-var API_KEY=12345

​
version

Display version information about FastMCP and related components.

fastmcp version