Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.mage.ai/llms.txt

Use this file to discover all available pages before exploring further.

1

Install mage-agent

pip install mage-agent
Verify the install:
mage-agent --version
2

Log in to your Mage Pro cluster

mage-agent login
The CLI prompts for your cluster URL, email, and password. On success, credentials are saved to ~/.mage-agent/config.json.
To skip the prompts, pass flags directly:
mage-agent login \
  --cluster-url https://your-mage-url \
  --email YOUR_EMAIL \
  --password YOUR_PASSWORD
3

Connect your AI assistant

Add the following to your IDE’s MCP server config and restart the client:
{
  "mcpServers": {
    "mage-agent": {
      "command": "mage-agent",
      "args": ["mcp"]
    }
  }
}
See IDE Integration for client-specific setup instructions.
4

Try it

Ask your AI assistant:
“List all my Mage pipelines”
“Create a new Python transformer block in the customer_etl pipeline”
“Run the daily_refresh pipeline and show me the logs”
The assistant calls the appropriate MCP tool automatically — no manual API calls required.

​
Next steps

Sync local files

Mirror your Mage project to your machine for local editing.

MCP tools reference

See every tool available to your AI assistant.