What inputs does get_compute_ready_stream accept?

dataset_type ("fact" | "ratio" | "filing" | "references" | "index_membership", required): Dataset to access. 'fact' requires ticker (per-entity partition). All others are full-universe tables. ticker (string, optional): Required when dataset_type is 'fact'. Resolves to the per-entity fact/{CIK}.parquet partition for that company.

Which Valuein plans include get_compute_ready_stream?

Available on every plan, including the free tier with no account. Not point-in-time safe.

Bulk Access

Compute-Ready Stream

get_compute_ready_stream

Sample and above

Returns a short-lived (15-min) download URL for a bulk Parquet object that can be piped directly into Python/DuckDB/Polars for high-throughput computation that exceeds the MCP context window. The URL streams the object straight from Valuein storage and supports HTTP range read...

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_compute_ready_stream",    arguments={    "dataset_type": "fact"})print(result)

Direct tool call:get_compute_ready_stream(dataset_type="fact", ticker="AAPL")

Try it now

No token required

Paste this in your terminal — the free tier returns real sample data without authentication.

try-it.shbash

# No auth required — the Sample tier covers a large-cap US benchmark universe with a 5-year window.# Add -H "Authorization: Bearer $VALUEIN_TOKEN" for the full universe and history.curl -X POST https://mcp.valuein.biz/mcp \    -H "Content-Type: application/json" \    -H "Accept: application/json, text/event-stream" \    -d '{        "jsonrpc": "2.0",        "id": 1,        "method": "tools/call",        "params": {          "name": "get_compute_ready_stream",          "arguments": {            "dataset_type": "fact",            "ticker": "AAPL"          }        }      }'

Inputs

Parameter	Type	Required	Description
`dataset_type`	"fact" \| "ratio" \| "filing" \| "references" \| "index_membership"	required	Dataset to access. 'fact' requires ticker (per-entity partition). All others are full-universe tables.
`ticker`	string	optional	Required when dataset_type is 'fact'. Resolves to the per-entity fact/{CIK}.parquet partition for that company.

Output Fields

dataset_typetickerbucketobject_keyurlscopeexpires_atexpires_in_secondsurl_hashformatusage

Example Response

Illustrative

response.jsonjson

{  "dataset_type": null,  "ticker": "AAPL",  "bucket": null,  "object_key": null,  "url": "https://r2.valuein.biz/signed/fact.parquet?token=...",  "scope": null,  "expires_at": "2024-03-15",  "expires_in_seconds": null}

Shape only — field names match the live schema; values are placeholders, not real filings. Returns a short-lived download URL for Apple's fact partition — load it directly with pd.read_parquet(url) or duckdb.read_parquet(url).

Notes

The URL expires after 15 minutes. `fact` is served one company at a time (pass `ticker`); the other datasets are full-universe tables, so read them lazily with filters (DuckDB) rather than loading a whole table into memory.