You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 6bed4c5
Browse filesBrowse the repository at this point in the historyBrowse files
fix(everything): gate trigger-elicitation-request on form-mode elicitation
trigger-elicitation-request sends a form-mode elicitation, but it was
registered whenever the client declared `elicitation` at all, so a client
that declared only URL mode saw the tool and every call failed. Register it
only when the client declared `elicitation.form`, or an `elicitation` object
with neither mode (form mode, per the spec's backwards-compatibility rule),
the same test the SDK client applies (#4985).
Flip the KNOWN BUG pins for #4792 and #4985 to the correct behavior,
update the instructions' gated-tools table and features.md for the form
requirement, and adapt the tests ported from #4835 to the file's static
imports and typed mocks.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Signed-off-by: cliffhall <[email protected]>
Server instructions no longer tell every client to use tools that are registered only for clients declaring a capability; they list those tools and the capability each needs (#4792, ported from #4835). `trigger-elicitation-request` is now registered only for clients that support form-mode elicitation, so a client that declared only URL-mode elicitation no longer sees a tool it cannot answer (#4985).
Copy file name to clipboardExpand all lines: src/everything/docs/features.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -22,7 +22,7 @@
22
22
-`trigger-long-running-operation` (tools/trigger-long-running-operation.ts): Simulates a multi-step operation over a given `duration` and number of `steps`; reports progress via `notifications/progress` when a `progressToken` is provided by the client.
23
23
-`toggle-simulated-logging` (tools/toggle-simulated-logging.ts): Starts or stops simulated, random‑leveled logging for the invoking session. Respects the client’s selected minimum logging level.
24
24
-`toggle-subscriber-updates` (tools/toggle-subscriber-updates.ts): Starts or stops simulated resource update notifications for URIs the invoking session has subscribed to.
25
-
-`trigger-elicitation-request` (tools/trigger-elicitation-request.ts): Issues an `elicitation/create` request using form-mode fields (strings, numbers, booleans, enums, and format validation) and returns the resulting action/content.
25
+
-`trigger-elicitation-request` (tools/trigger-elicitation-request.ts): Issues an `elicitation/create` request using form-mode fields (strings, numbers, booleans, enums, and format validation) and returns the resulting action/content. Requires client form-mode elicitation: `elicitation.form`, or an `elicitation` object that declares neither mode.
26
26
-`trigger-url-elicitation` (tools/trigger-url-elicitation.ts): Issues an `elicitation/create` request in URL mode (`mode: "url"`) with an `elicitationId`, or throws MCP error `-32042` (`UrlElicitationRequiredError`) when `errorPath=true`. On the error path the prerequisite elicitation it returns points at a different URL than the failing request (`https://modelcontextprotocol.io`); when the client satisfies it and retries the same call, the retry ignores `errorPath` and proceeds via the request path, so the client does not loop on the same error. The retry marker is one-shot per `(session, url, elicitationId)`: it is cleared on the recognized retry, so re-running the error path with identical arguments without an intervening prerequisite is treated as a retry and proceeds. Requires client capability `elicitation.url`.
27
27
-`trigger-sampling-request` (tools/trigger-sampling-request.ts): Issues a `sampling/createMessage` request to the client/LLM using provided `prompt` and optional generation controls; returns the LLM's response payload.
28
28
-`simulate-research-query` (tools/simulate-research-query.ts): Demonstrates MCP Tasks (SEP-1686) with a simulated multi-stage research operation. Accepts `topic` and `ambiguous` parameters. Returns a task that progresses through stages with status updates. If `ambiguous` is true and client supports elicitation, sends an elicitation request directly to gather clarification before completing.
0 commit comments