Deploy AI agents

Deploy a FastAPI MCP server on DenkOps

The official Python `mcp` SDK's streamable-HTTP transport expects a server process that stays up between requests so it can track session state across a conversation. A DenkOps slot is that process, no cold start resets the session store, so an agent's MCP connection behaves the same on request one hundred as it did on request one.

from fastapi import FastAPI
from mcp.server.fastmcp import FastMCP

mcp = FastMCP("denkops-tools")

@mcp.tool()
def get_status(node_id: str) -> str:
    return f"node {node_id} is running"

app = FastAPI()
app.mount("/mcp", mcp.streamable_http_app())

Deploy it: install the plugin, say "deploy on DenkOps", and get a live SSL URL.

FAQ

Can I mount the Python mcp SDK on FastAPI and deploy it on DenkOps?

Yes. FastMCP's streamable-HTTP ASGI app mounts directly onto your FastAPI app, and the slot keeps the whole process alive for the agent's session.

Does session state survive between MCP tool calls on DenkOps?

Yes, because the process never restarts between requests, in-memory session and tool state persists for the life of the agent's connection.

← Deploy AI agents · API hosting