Discovery
Score Claim
score_claimBenchmark and above
Resolve a claim's outcome. By default auto-grades an `auto` claim by evaluating its verifiable_condition against SEC fundamentals (confirmed/refuted), or marks it `needs_review` when it can't be resolved deterministically (judgment, antecedent, or missing data). To record a hu...
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( "score_claim", arguments={ "claim_id": "EXAMPLE"})print(result)Direct tool call:score_claim(...)
Inputs
| Parameter | Type | Required | Description |
|---|---|---|---|
claim_id | string | required | Id of the claim to resolve. |
as_of | string | optional | Snapshot date for the fundamentals window (auto mode). Defaults to today UTC. |
manual_status | "confirmed" | "refuted" | "expired" | "stale" | "needs_review" | optional | Provide to record a human/agent outcome instead of auto-grading. |
manual_score | number|null | optional | Outcome score in [-1,1] for a manual resolution. Null for non-scored statuses. |
manual_reason | string | optional | Explanation for a manual resolution. |
Output Fields
claimmoderesolved_statusscorebasisreasondeduplicatedExample Response
Illustrative
response.jsonjson
{ "claim": null, "mode": null, "resolved_status": null, "score": null, "basis": null, "reason": null, "deduplicated": null}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.