Skip to main content
Score ideas from a script or backend: viability score, competitors, source-linked evidence. One bearer token, no SDK. For Claude, Cursor, or Codex, use Get started instead.
1

Get your key

Calling the API from your own code needs a key you create yourself. Make one at Account → API Keys or, in a Consultant or Agency workspace, at Dashboard → API keys. Either works on a paid personal plan or in a Consultant or Agency workspace with an active subscription or a one-time unlock. The prv_... value is shown once. Send it as Authorization: Bearer prv_... (see Authentication).
Copy the key when you create it. It’s shown once. Keep it out of git and out of browser code.
Connecting the Preuve connector instead works on a free account, but it mints the key inside your MCP client and never shows you the value, so there is nothing to send as a bearer token. For that path, start at Get started.
2

Create an analysis

scanType is required: "starter" is free, "deep" spends paid quota. clientRunId is how you retry: sending the same value again returns the existing run instead of starting a second one. Optional context fields sharpen the report: stage (idea | validation | mvp | launched | growth | scaling) and budget (bootstrap | 10k | 50k | 100k | 100kPlus | 1mPlus) feed the feasibility analysis directly, and the MCP tools make both required on a deep scan unless it is an Agency client project (workspace: "agency"), which keeps both optional, as free text. On POST /api/agent/analyses, an optional workspace (personal or agency) decides where a deep scan runs: leave it out and a key with agency:write on an Agency workspace member starts a client project there, send personal to keep the scan on the account’s own deep scans.
No terminal handy? The same calls run in the browser on the RapidAPI playground or from the Postman workspace: paste your prv_... key into the Authorization tab. Both listings are free; what you spend is your Preuve quota, same as from code.
3

Poll until complete

Starter runs typically complete in 1-3 minutes, deep runs in 5-10. Poll every 10-15 seconds until status is COMPLETED.
4

Enrich, then export

You get stable JSON (schemaVersion: 2): score, verdict, competitors, risks, and citations. Deep scans also include the full report, pivots, and any modules. See Scans and enrichment.

Next steps

MCP server

Same verdict, from the chat you are already in.

Batches

Score up to 5 ideas over HTTP and rank them by viability.

Deep modules

Proof of Demand, Founder Fit, Playbook, and Trends on demand.

Quotas and billing

What gets charged, and what gets refunded.