Skip to content

Commit fb58c4f

Browse files
docs: qualify the with-provider 403 behavior
1 parent 27c2eb0 commit fb58c4f

2 files changed

Lines changed: 2 additions & 2 deletions

File tree

‎.changeset/probe-auth-status-not-era-evidence.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -17,7 +17,7 @@ keyed on that code cannot persist a verdict for an unauthorized exchange. A
1717
modern server to legacy — the legacy fallback now fires only on the 4xx
1818
shapes the spec licenses.
1919

20-
With an `authProvider`, the transport's auth flow runs first and whatever
20+
With an `authProvider`, a `401` (and a `403` `insufficient_scope` challenge) runs the transport's auth flow first — a plain `403` rejects the same as without a provider — and whatever
2121
escapes it propagates unchanged, identity intact: the HTTP transports stamp
2222
errors at their auth seams (the `token()` read, `onUnauthorized` including
2323
custom callbacks, the 403 step-up flow, and their own auth-failure

‎docs/protocol-versions.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -101,7 +101,7 @@ const cli = new Client(
101101

102102
A probe timeout is transport-aware. On stdio a silent server is a legacy server, so `connect()` falls back to `initialize`; on HTTP silence is an outage, so `connect()` rejects with `SdkError(RequestTimeout)` instead of misreporting a dead server as legacy. One browser exception: an opaque CORS `TypeError` during the probe falls back to the legacy era, because deployed 2025 servers commonly have allow-lists that predate the 2026 headers.
103103

104-
Auth statuses are not era evidence either. An HTTP `401` or `403` rejecting the probe surfaces as a typed authorization failure, never the legacy fallback — and never as `EraNegotiationFailed`, so era-recovery flows keyed on that code (the [gateway guide](./advanced/gateway.md) recipe) cannot consume an auth wall. A plain `401` or `403` with no `authProvider` rejects `connect()` with an `SdkHttpError` carrying the status: code `ClientHttpAuthentication` for `401`, `ClientHttpForbidden` for `403`. One 403 shape is different: a `WWW-Authenticate` challenge with `error="insufficient_scope"` enters the Streamable HTTP transport's step-up flow regardless of provider, and with none it rejects with the flow's typed `InsufficientScopeError`. With a provider, the auth flow runs first and whatever escapes it reaches you as thrown, identity intact — the transport stamps errors at its auth seams (the `token()` read, `onUnauthorized` including custom callbacks, step-up), so `UnauthorizedError` for `finishAuth()`, the flow's typed failures (`OAuthError`, `InsufficientScopeError`, the 401-after-re-authentication diagnostic), and even an untyped crash inside a callback all propagate unchanged. A `5xx` rejecting the probe is a server failure, not era evidence: `connect()` rejects with `SdkHttpError(EraNegotiationFailed)` naming the status. These status-keyed rows read the transport's typed HTTP rejections — the SDK's Streamable HTTP transport surfaces them with the status attached; the legacy SSE client transport reports a non-2xx POST as a generic error, so over SSE a probe rejection surfaces as the generic `Version negotiation probe failed` connect error instead. Auth settles first, era second: a `401` never decides the era — the auth wall answers before the MCP layer ever sees `server/discover` — and the post-auth re-probe supplies the real era evidence.
104+
Auth statuses are not era evidence either. An HTTP `401` or `403` rejecting the probe surfaces as a typed authorization failure, never the legacy fallback — and never as `EraNegotiationFailed`, so era-recovery flows keyed on that code (the [gateway guide](./advanced/gateway.md) recipe) cannot consume an auth wall. A plain `401` or `403` — with or without an `authProvider` — rejects `connect()` with an `SdkHttpError` carrying the status: code `ClientHttpAuthentication` for `401`, `ClientHttpForbidden` for `403`. One 403 shape is different: a `WWW-Authenticate` challenge with `error="insufficient_scope"` enters the Streamable HTTP transport's step-up flow regardless of provider, and with none it rejects with the flow's typed `InsufficientScopeError`. With a provider, a `401` (and a `403` `insufficient_scope` challenge) runs the auth flow first, and whatever escapes it reaches you as thrown, identity intact — the transport stamps errors at its auth seams (the `token()` read, `onUnauthorized` including custom callbacks, step-up), so `UnauthorizedError` for `finishAuth()`, the flow's typed failures (`OAuthError`, `InsufficientScopeError`, the 401-after-re-authentication diagnostic), and even an untyped crash inside a callback all propagate unchanged. A `5xx` rejecting the probe is a server failure, not era evidence: `connect()` rejects with `SdkHttpError(EraNegotiationFailed)` naming the status. These status-keyed rows read the transport's typed HTTP rejections — the SDK's Streamable HTTP transport surfaces them with the status attached; the legacy SSE client transport reports a non-2xx POST as a generic error, so over SSE a probe rejection surfaces as the generic `Version negotiation probe failed` connect error instead. Auth settles first, era second: a `401` never decides the era — the auth wall answers before the MCP layer ever sees `server/discover` — and the post-auth re-probe supplies the real era evidence.
105105

106106
On the SDK's own stdio transport (exactly `StdioClientTransport` — subclasses, like custom stdio-shaped transports, probe in place) the probe runs on a short-lived **sibling process** spawned from the same parameters — some stdio servers exit on any pre-`initialize` request (servers built on the official Rust SDK, rmcp, behave this way), so the probe must not spend the caller's one child process. The sibling is invisible infrastructure: its stderr is discarded and it is reaped once the era is known; the caller's transport spawns exactly once, afterwards, and its wire never carries `server/discover`. A child that exits on the probe is simply a legacy server (its exit must close the child's stdio pipes to register — an exit hidden behind a helper process holding them open falls to the probe-timeout path). Closing the caller's transport during the probe aborts `connect()` with a typed `SdkError(EraNegotiationFailed)` and the session child is never spawned. On HTTP — and on custom stdio-shaped transports, which probe in place — a mid-probe connection close rejects with the same typed error as any probe transport failure.
107107

0 commit comments

Comments
 (0)