Discovery
Get Auditable Research File
get_research_fileBenchmark and above
Fetch the Auditable Research File behind one of the caller's own agent runs — the complete evidence chain an examiner asks for: the originating prompt, every tool the agent called in order, every `fact_id` it cited, every human approval, and which models were used. Assembled f...
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( "get_research_file", arguments={})print(result)Direct tool call:get_research_file(...)
Inputs
| Parameter | Type | Required | Description |
|---|---|---|---|
report_id | string | optional | Report identifier — from create_report, list_my_reports or search_reports. Resolves the run behind that report and adds the human_review + sources sections. Pass this OR run_id, not both. |
run_id | string | optional | Run identifier, as returned by list_agent_runs. Pass this OR report_id, not both. |
format | "json" | "pdf" | optional | json (default) = the assembled file inline. pdf = a presigned download URL for the branded compliance PDF — the human-facing artifact; rendered fresh on every call, never cached.Default: "json" |
Output Fields
foundrun_idfileurlfilenamecontent_typesize_bytesexpires_in_secondsexpires_atExample Response
Illustrative
response.jsonjson
{ "found": null, "run_id": null, "file": null, "url": "https://r2.valuein.biz/signed/fact.parquet?token=...", "filename": null, "content_type": null, "size_bytes": null, "expires_in_seconds": 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.