modelcontextprotocol / modelcontextprotocol/conformance
No client-suite scenarios for the tasks extension (io.modelcontextprotocol/tasks)
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 127
- Forks
- 101
- Avg merge
- 6d 1h
- Merged PRs (30d)
- 7
Description
The server suite has 10 tasks-* scenarios, but the client suite has none. SEP-2663 places normative requirements on clients too — most importantly:
A client that has negotiated this extension MUST be prepared to handle either
CallToolResultorCreateTaskResultin response to any supported request it issues.
plus the tasks/get polling flow (pollIntervalMs handling), issuing tasks/update / tasks/cancel, and the Mcp-Name: <taskId> routing header on tasks/* requests.
python-sdk is landing a client-side transparent polling driver (modelcontextprotocol/python-sdk#3005) and currently has no way to verify it against the harness — client conformance can't observe any of the above.
Suggested client-suite scenarios:
tasks-client-create-handling— the harness server task-augments atools/call; the client must handle theCreateTaskResultand fetch the result viatasks/get.tasks-client-poll-interval— the client honorspollIntervalMsbetween polls.tasks-client-routing-headers— the client stampsMcp-Name: <taskId>ontasks/*POSTs.tasks-client-terminal-handling—failed/cancelledtasks are surfaced rather than polled forever.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading SEP-2663 and the existing server-suite tasks-* scenarios, then locate the client-suite scenario definitions and harness flow. Add coverage for CreateTaskResult handling, pollIntervalMs, Mcp-Name routing, and failed or cancelled terminal tasks; done means the client suite exercises all four behaviors.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- api, testing-qa
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 68/100