Compute-Ready Stream
get_compute_ready_streamReturns 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
# 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={ "table": "EXAMPLE"})print(result)Direct tool call:get_compute_ready_stream(table="fact")
Try it now
Paste this in your terminal — the free tier returns real S&P500 data without authentication.
# No auth required — sample tier covers S&P500 with a 5-year window.# Add an Authorization: Bearer header for full universe and history.$ curl -X POST https://mcp.valuein.biz/mcp \ -H "Content-Type: application/json" \ -d '{ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "get_compute_ready_stream", "arguments": { "table": "AAPL" } } }'Inputs
| Parameter | Type | Required | Description |
|---|---|---|---|
table | string | required | Table name. Core: entity, security, filing, fact, valuation, taxonomy_guide, index_membership, references. Derived: ratio, factor_scores, earnings_signals. |
format | string | optional | Output format: parquet (default) or wide_parquet for pre-pivoted wide tables. |
Output Fields
urlexpires_attableplanestimated_size_mbExample Response
{ "url": "https://r2.valuein.biz/signed/fact.parquet?token=...", "expires_at": "2024-03-15", "table": "fact", "plan": "sp500", "estimated_size_mb": 342}Shape only — field names match the live schema; values are placeholders, not real filings. Returns a presigned URL for fact.parquet — load directly with pd.read_parquet(url) or duckdb.read_parquet(url).
Notes
URL expires in 60 minutes. The fact table is large (several GB on full plan) — use DuckDB's lazy reading with filters rather than loading the full table into memory.