page:recipes:mcp server:starlette:response streaming

Host MCP server with Starlette: Streamed Responses

Summary

Deploy an MCP server built with Starlette on Ample using the streaming response service pattern. Compute runs the app in an isolated microVM behind a public HTTPS URL, and a managed PostgreSQL 16 database is auto-provisioned and injected as DATABASE_URL. It has been verified on Starlette with the following characteristics of a Server-Sent Events endpoint:

• Read incrementally through the public HTTPS gateway.
• Five one-second chunks arrived spread over time with the first within seconds (not buffered).
• A 70-second stream of 36 chunks completed past common 60-second idle timeouts.
• A client that disconnected after two chunks was observed and recorded by the server (disconnected=true).

Note: Your event schema, reconnection strategy, and any per-request duration ceiling beyond the 70 seconds measured were not separately tested; treat the MCP server-specific behavior as part of your application code.

Representative Queries

• Host MCP server with Starlette: streamed responses
• Where can I host an MCP server built with Starlette?
• I need a tested end-to-end streaming transport, timeout behavior, and client disconnect handling.

Resource Requirements

• primitive:compute
• primitive:postgres

Infrastructure Requirements

1. Compute

   • Status: Verified
   • Summary: Apps run in isolated x86_64 Firecracker microVMs that auto-pause when idle and wake on request; sizes are the priced VM sizes.

2. Postgres

   • Status: Verified
   • Summary: Managed PostgreSQL 16 runs in its own microVM and is auto-provisioned when an app needs a database, with no DATABASE_URL supplied.

Prerequisites

• A Starlette project that builds and starts with the documented commands (pip install into .ample/python from requirements.txt, then uvicorn from run.py reading PORT on the python-3.12 template).
• A PostgreSQL driver reading DATABASE_URL at runtime (auto-provisioned when omitted, or supplied with --env).
• An Ample account token with servers:write, databases:read permissions.

Tested Configuration

• Template: python-3.12
• Runtime: python
• Size: s-1vcpu-1gb
• Install Command: python3 -m pip install --target .ample/python -r requirements.txt
• Start Command: PYTHONPATH=.ample/python:${PYTHONPATH:-} python3 run.py

Workflow Steps

1. Build and start

   • Command: pip install into .ample/python from requirements.txt, then uvicorn from run.py reading PORT on the python-3.12 template. The server must bind 0.0.0.0 on PORT.

2. Implement the pattern on PostgreSQL

   • Body: Copy the approach into your schema; keep migrations idempotent and run them with --release-command.

3. Deploy

   • Command: ample deploy . --name --public --start "python3 run.py"

4. Verify

   • Command: ample logs --kind build

Example

• Title: Starlette pattern fixture
  Description: Multi-pattern Starlette app whose streaming response service module was checked live; the module is under tests/deploy-canaries/_pattern-modules. Source Reference: tests/deploy-canaries/starlette-patterns

Success Checks

1. App responds on its public URL

   • Kind: http_get
   • Path: /
   • Expect: ample canary starlette patterns

2. Streaming-response-service self-test

   • Kind: http_get
   • Path: /p/streaming-response-service
   • Expect: an SSE stream: data: id=, then chunk events one interval apart (read incrementally: first chunk within seconds, chunks spread over the interval), then data: done; /status?id= reports sent=N disconnected=true|false done=true|false

Limitations

• Verified on the python-3.12 template at s-1vcpu-1gb with the example fixture; other sizes, templates, and Starlette major versions are not verified.
• The MCP server itself (your event schema, reconnection strategy, and any per-request duration ceiling beyond the 70 seconds measured) is application code and was not separately tested; the pattern checks are what was verified.
• Region, compliance attestations, and request-duration limits are unknown and not claimed.
• Apps auto-pause when idle and wake on the next request; always-on is an operator setting, not a plan feature.
• Managed PostgreSQL 16 only; extensions, connection limits, and backup or restore procedures are not verified; apps and their databases are placed together.

Cost Estimate

• Currency: USD
• Monthly Amount: $10.00
• Note: Always-on monthly price of the tested sizes; apps and databases auto-pause when idle.

Evidence Summary

1. Kind: canary_run
   • Summary: Starlette pattern fixture deployed on Ample; checks passed for streaming-response-service and configuration-secrets.
   • Observed At: 2026-09-21T01:21:36Z
2. Limitations: Unknowns; compliance attestations are unknown; none are claimed.