Python / FastAPI
Learn how to deploy a FastAPI application with Ink MCP using a simple prompt.
Create an Ink account and connect MCP
Make sure you have an Ink account and have connected Ink MCP to your agent. There are two ways to connect:
- OAuth — authenticate through a browser flow, no keys to manage
- Token — create an API key at ml.ink/account/api-keys
See Quick Start for full setup instructions.
Verify the connection
Once the MCP server is connected, confirm your agent can reach it by asking it to check.
Do you have Ink MCP connected?
Create a FastAPI app
Ask your agent to scaffold a new FastAPI project. If you already have a Python app in the current directory, skip this step and go straight to deploying.
Create a FastAPI app with endpoints for managing a bookmarks collection. Include Pydantic models for validation and automatic OpenAPI docs.
Deploy with Ink
Tell your agent to deploy. The agent will create a git repository on Ink's internal git (or your connected GitHub), push the code, and call create_service to trigger a build.
Ink auto-detects Python and starts the app with uvicorn.
Deploy with Ink
create_repo(
"name": "bookmarks-api"
)create_service(
"name": "bookmarks-api",
"repo": "ink/bookmarks-api",
"build_pack": "railpack",
"port": "3000"
)Visit your API
Ink returns a live URL once the build completes. Visit /docs to see the auto-generated OpenAPI documentation.
Check logs and metrics (optional)
Ask your agent to pull build logs, runtime logs, or metrics for your deployed service.
Check metrics and logs
get_service(
"name": "bookmarks-api",
"deploy_log_lines": "50",
"runtime_log_lines": "50"
)That's it — your FastAPI app is deployed and live. From here you can add a custom domain, set up environment variables, or explore more examples.