Click Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Click Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A Python library that extends Click applications with Model Context Protocol (MCP) support, allowing AI agents to interact with CLI tools.
click-mcp provides a simple decorator that converts Click commands into MCP tools. This enables AI agents to discover and interact with your CLI applications programmatically.
The Model Context Protocol (MCP) is an open standard for AI agents to interact with tools and applications in a structured way.
@click_mcp decorator syntaxpip install click-mcpimport click
from click_mcp import click_mcp
@click_mcp(server_name="my-cli-app")
@click.group()
def cli():
"""Sample CLI application."""
pass
@cli.command()
@click.option('--name', required=True, help='Name to greet')
def greet(name):
"""Greet someone."""
click.echo(f"Hello, {name}!")
if __name__ == '__main__':
cli()When you run the MCP server, Click commands are converted into MCP tools:
greet becomes MCP tool greetusers.create)To invoke a command via MCP, send a request like:
{
"type": "invoke",
"tool": "greet",
"parameters": {
"name": "World"
}
}To start the MCP server:
$ python my_app.py mcpBy default, click-mcp adds an mcp command to your CLI application. You can customize this name using the command_name parameter:
@click_mcp(command_name="start-mcp")
@click.group()
def cli():
"""Sample CLI application with custom MCP command name."""
passWith this configuration, you would start the MCP server using:
$ python my_app.py start-mcpThis can be useful when:
You can also customize the name of the MCP server that's reported to clients:
@click_mcp(server_name="my-custom-tool")
@click.group()
def cli():
"""Sample CLI application with custom server name."""
passThis can be useful when:
click-mcp supports nested command groups. When you have a complex CLI structure with subcommands, all commands are exposed as MCP tools:
@click_mcp
@click.group()
def cli():
"""Main CLI application."""
pass
@cli.group()
def users():
"""User management commands."""
pass
@users.command()
@click.option('--username', required=True)
def create(username):
"""Create a new user."""
click.echo(f"Creating user: {username}")
@users.command()
@click.argument('username')
def delete(username):
"""Delete a user."""
click.echo(f"Deleting user: {username}")When exposed as MCP tools, the nested commands will be available with their full path using dot notation (e.g., "users.create" and "users.delete").
Click supports positional arguments using @click.argument(). When these are converted to MCP tools, they are represented as named parameters in the schema:
@cli.command()
@click.argument('source')
@click.argument('destination')
@click.option('--overwrite', is_flag=True, help='Overwrite destination if it exists')
def copy(source, destination, overwrite):
"""Copy a file from source to destination."""
click.echo(f"Copying {source} to {destination}")This command is converted to an MCP tool with the following schema:
{
"type": "object",
"properties": {
"source": {
"description": "",
"schema": { "type": "string" },
"required": true
},
"destination": {
"description": "",
"schema": { "type": "string" },
"required": true
},
"overwrite": {
"description": "Overwrite destination if it exists",
"schema": { "type": "boolean" }
}
},
"required": ["source", "destination"]
}The positional nature of arguments is handled internally by click-mcp. When invoking the command, you can use named parameters:
{
"type": "invoke",
"tool": "copy",
"parameters": {
"source": "file.txt",
"destination": "/tmp/file.txt",
"overwrite": true
}
}The MCP server will correctly convert these to positional arguments when executing the Click command:
copy file.txt /tmp/file.txt --overwriteWhen a Click command raises an exception, click-mcp captures the error and returns it as part of the MCP response. This allows AI agents to handle errors gracefully:
@cli.command()
@click.option('--filename', required=True)
def process(filename):
"""Process a file."""
try:
with open(filename, 'r') as f:
content = f.read()
click.echo(f"Processed file: {filename}")
except FileNotFoundError:
raise click.UsageError(f"File not found: {filename}")If the file doesn't exist, the AI agent will receive an error message that it can present to the user or use to take corrective action.
Clone the repository and install Hatch:
git clone https://github.com/aws/click-mcp.git
cd click-mcp
pip install hatchRun tests with Hatch:
# Run all tests
hatch run test
# Run tests with coverage
hatch run covFormat code with Black:
# Format code
hatch run format
# Check formatting
hatch run check-formatRun linting checks with Ruff:
hatch run lintRun type checking with MyPy:
hatch run typecheckRun all checks (formatting, linting, type checking, and tests):
hatch run check-allBuild the package:
hatch run buildGenerate documentation:
hatch run docsMIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.