Sticky sessions, GET streams and resume on the modern wire
RolesAgent Systems EngineeringCustomer AI Deployment
The question
A platform team deploys an MCP server over Streamable HTTP behind a load balancer with two replicas. They configure sticky routing keyed on Mcp-Session-Id, keep a standalone GET /mcp stream for change notifications, and plan to resume a broken stream with Last-Event-ID. Which of these belong to the current revision, and what replaces the rest?
Answer it first, aloud or on paper. Then open the answer.
The answer
Show short answer
None of the three belongs to the current revision. The endpoint accepts POST only: GET /mcp and DELETE /mcp return 405, Mcp-Session-Id is ignored and never minted, and Last-Event-ID is ignored because streams do not resume. Change notifications arrive on a client-opened subscriptions/listen POST whose response stays open as SSE, and a dropped stream is replaced by a new listen request and a refetch of the affected data.
Show full answer
The modern wire in one table
| Message | HTTP shape |
|---|---|
| any JSON-RPC request | a new POST with one message in the body |
| the response | application/json with one response, or text/event-stream with related notifications and then the final response |
| an accepted notification | 202 Accepted with no body |
GET or DELETE on the endpoint | 405 Method Not Allowed |
The client advertises both response types with Accept: application/json, text/event-stream.
Why stickiness is not needed
Every request carries its protocol version and client capabilities in params._meta, so any healthy worker can validate it. Three headers mirror the body for routing and policy: MCP-Protocol-Version, Mcp-Method, and Mcp-Name for tools/call, resources/read and prompts/get. The server compares each header with the body before it executes. A missing or mismatched header is HTTP 400 with JSON-RPC -32020.
Where notifications come from
The client sends subscriptions/listen as a normal request with a notifications filter, for example toolsListChanged: true and a list of resourceSubscriptions. The first message on the stream is notifications/subscriptions/acknowledged. Every event and the final result carry io.modelcontextprotocol/subscriptionId, equal to the listen request id. When the stream drops, the client reissues the request with a new id and refetches tools, resources or prompts. resources/subscribe belongs to the legacy era.
What a broken request-scoped stream means
The in-flight request is lost. The client may issue a new request with a new JSON-RPC id when a retry is safe. It must not attempt stream resumption, and the server must not add SSE ids for replay.
Two more rules at the boundary
- Validate
Originwith exact matching, and return403when it is present and not allowed. Local servers bind to127.0.0.1. This defends against DNS rebinding and is not authentication. - Keep a legacy HTTP+SSE bridge, if you need one, on separate endpoints, and never describe its GET stream, session id or replay as part of the current revision.
Follow-ups
L2WorkingHow does a client cancel an in-flight request over this transport?
Show expected answer
it closes that request's response stream; there is no cancellation POST.
L3SeniorWhy is a
startswithtest on the trusted origin unsafe?Show expected answer
it accepts an attacker-controlled suffix on the host name; match the canonical origin exactly.
L3SeniorA dual-era client receives
405from an unknown server. Does it fall back to the old GET endpoint?Show expected answer
only after reading the body; a recognized modern JSON-RPC error proves the server is modern, and only an empty or unrecognized body justifies the legacy attempt.
L4StaffA workflow needs state across two calls on two replicas. Where does it live?
Show expected answer
behind a server-minted opaque handle in a shared store, returned as an ordinary result, bound to the principal, expired, and authorized on each use.
Wrong answers
Show the wrong answers that interviewers hear
“Sticky routing is harmless, so keep it as a safety net.”
It hides a correctness bug until a rollout, a reschedule or a failover moves the next request to another replica.
“Add SSE event ids so that clients can resume.”
Modern streams are not resumable. A lost request is retried with a new id when the operation allows it.
“Origin validation authenticates the caller.”
It stops DNS rebinding only. A network service still authenticates and authorizes every request.
Taught in
The transports lesson defines the POST-only endpoint, the mirrored headers and the subscriptions/listen stream.