AI Chatbot
Learn how to deploy an AI chatbot 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?
Build the chatbot
Ask your agent to build an AI chatbot. The agent will scaffold a Next.js app with the Vercel AI SDK and a streaming chat interface.
Build a chatbot web app using Next.js and the Vercel AI SDK. Use Anthropic's Claude as the LLM. Include a clean chat interface with streaming responses.
Deploy with Ink
Tell your agent to deploy. The app needs an ANTHROPIC_API_KEY environment variable to call the Claude API.
Deploy with Ink. Use my Anthropic API key.
create_service(
"name": "chatbot",
"repo": "ink/chatbot",
"build_pack": "railpack",
"port": "3000",
"env_vars": {
"ANTHROPIC_API_KEY": "sk-ant-..."
}
)Visit your chatbot
Ink returns a live URL once the build completes. Visit it to start chatting with your AI-powered chatbot.
Check logs and metrics (optional)
Ask your agent to pull build logs, runtime logs, or metrics for your deployed service.
Check metrics and logs
That's it — your AI chatbot is deployed and live. From here you can add a custom domain, set up additional environment variables, or explore more examples.