Discovery
Schedule Task
schedule_taskBenchmark and above
Defer a follow-up task ("re-check AAPL margin compression in 30 days") for up to ${MAX_WAKE_HORIZON_DAYS} days. This is an AGENT-facing primitive — call it mid-conversation/mid-run when you decide something is worth re-checking later; it is NOT a human-authorable "new task" fo...
Example Call
example_call.pypython
# Using the Valuein MCP server from Python (via MCP SDK)# Or call directly from Claude / Cursor after setup result = await client.call_tool( "schedule_task", arguments={ "task": "EXAMPLE", "wake_in_days": 10})print(result)Direct tool call:schedule_task(...)
Inputs
| Parameter | Type | Required | Description |
|---|---|---|---|
task | string | required | Human-readable description of the deferred work. |
wake_in_days | number | required | How many days from now this task becomes due (0 < n <= 90). |
context | object | optional | Saved thesis/claim/report ids and any other state needed to reconstitute a fresh prompt at wake time. Set `managed: true` + `team_id: "<standing_agent id>"` to also kick off a live managed re-run of that team at wake time (see description). |
Output Fields
task_idwake_atstatusExample Response
Illustrative
response.jsonjson
{ "task_id": null, "wake_at": "2024-03-15", "status": "ACTIVE"}Shape only — field names match the live schema; values are placeholders, not real filings. See MCP server for the structured response shape.
Notes
Available from the Benchmark plan and above.
Plan Access
Sample (guest)
Not includedBenchmark (token)
AvailablePro
AvailableInstitutional
AvailableRelated Tools
Index names are trademarks of their owners; Valuein is not affiliated with or endorsed by any index provider.