Describe how Streamable HTTP works as an MCP transport and when to choose it

Attempt it

Explain how Streamable HTTP functions as an MCP transport, what HTTP mechanism enables streaming, and describe a concrete deployment where it is the correct choice versus stdio.

Free · 2 AI evals / day

Quick reference

TL;DR

Streamable HTTP is one endpoint the client POSTs JSON-RPC to; the server replies with plain JSON or upgrades to SSE for streaming, making remote and serverless MCP servers practical.

Memory aid

Sign in for the mnemonic that makes this stick. See Pro pricing.

Easy to grasp

Picture a drive-through window instead of a dedicated phone line into the kitchen. You pull up to one window and place your order (POST a request). For a quick item, the cook hands it straight back. For something that takes a while, they keep passing you pieces as they finish, so you are not stuck staring at a blank window. The old design needed a permanent open phone line plus a separate window, which is awkward when many cooks share the work or the kitchen shuts down between orders. The single-window design works even if a different cook handles each visit, because your receipt number tells everyone which order is yours. That is the whole trick: one door, optional trickle-back, and a ticket that survives across cooks.

Key concepts

Streamable HTTP transport JSON-RPC 2.0 Server-Sent Events MCP session continuity

Quick scan · 2–4 min

Everything important, quickly.

4 min: single POST endpoint + JSON-or-SSE response choice + Mcp-Session-Id continuity and resumability + why it beats old HTTP+SSE on serverless + stdio contrast.

Side-by-side

Concern	Streamable HTTP	Old HTTP+SSE	stdio
Endpoints	One POST endpoint	POST endpoint plus GET SSE channel	stdin and stdout of a child process
Streaming	Optional SSE upgrade per request	Always via the separate SSE channel	Line-delimited over the pipe
Session	Mcp-Session-Id header	Tied to the held-open SSE socket	Bound to the process lifetime
Serverless fit	Works; no pinned connection	Poor; needs a long-lived stream	Impossible; needs local spawn
Load balancers	Any worker serves any request	Splits the two endpoints awkwardly	Not applicable, local only

Real-world examples

Real products, models, and research that use this idea.

GitHub's remote MCP server runs on Cloudflare Workers and uses Streamable HTTP so hosts POST tool calls over HTTPS.
Cloudflare's Agents SDK ships a Streamable HTTP MCP server template that deploys to Workers without a held-open connection.
Claude Code and Claude Desktop connect to remote MCP servers over Streamable HTTP with OAuth on the same endpoint.

Interviewer follow-ups

What an interviewer would ask next. Try answering before peeking at the approach.

QHow does resumability work after a Streamable HTTP stream drops mid-response?

Sign in or go Pro to see the approach for this follow-up.

QWhy can a stateless server fleet behind a load balancer still hold MCP sessions?

Sign in or go Pro to see the approach for this follow-up.

QHow does OAuth 2.1 layer onto a remote Streamable HTTP MCP server?

Sign in or go Pro to see the approach for this follow-up.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

Sign in for 5 unlocks/day or go Pro for unlimited revision sheets. See Pro pricing.

References

Primary sources. Skim if you want the original framing.