Name: Preuve AI Market Research
Author: preuve

Что умеет

Start Analysis: Create one analysis run on Preuve AI. Returns { id, reportId, scanType, status, ... }. Runs are async: poll with get_analysis until status is COMPLETED. scanType "deep" spends paid quo

Get Analysis: Poll one analysis by run id or report id. Returns status (PROCESSING/COMPLETED/FAILED), readyForExport, enrichment progress, and report/share URLs. Note: an in-flight deep run reports an

Enrich Analysis: Idempotently generate missing core enrichment sections for a completed analysis (use when get_analysis reports readyForExport: false, then poll again). Optionally request bundled deep

Preuve AI is market research and competitive intelligence your agent can run mid-conversation, for founders pressure-testing an idea, and the engine agencies, accelerators and consultants use to pre-qualify inbound startups at scale.

One tool call runs an idea through 60+ live sources: demand signals, competitor landscape, market sentiment, pricing, funding activity, and risks. The output is a viability score, a clear verdict, and a report where every finding links to a source you can verify. Evidence, not another model's opinion.

8 tools: start_analysis, get_analysis, enrich_analysis, export_analysis, create_batch, get_batch, export_batch, generate_ideas.

Per analysis: viability score, verdict, competitor map (up to 15), source-linked demand evidence, risk assessment, pivot options. Deep modules on request: proof of demand (named prospects, quoted and linked), founder fit, launch playbook, Google Trends, community signals. Batch tools score entire idea lists, built for deal-flow qualification. No idea to test yet? generate_ideas returns ideas matched to your interests.

Safe by default: starter scans are free and are what every call defaults to. Your agent never spends paid quota unless you explicitly ask for a deep report.

Auth: OAuth 2.1 (sign in from claude.ai on a free account, no key handling) or an API key from your account. Docs: preuve.ai/mcp

Preuve AI Market Research

Что умеет

Какие данные видит

Нужен ли аккаунт

start_analysis	Create one analysis run on Preuve AI. Returns { id, reportId, scanType, status, ... }. Runs are async: poll with get_analysis until status is COMPLETED. scanType "deep" spends paid quota — default to "starter" unless the caller explicitly wants a deep scan.
get_analysis	Poll one analysis by run id or report id. Returns status (PROCESSING/COMPLETED/FAILED), readyForExport, enrichment progress, and report/share URLs. Note: an in-flight deep run reports analysisTier "basic" until deep sections land — use scanType as the request-type signal.
enrich_analysis	Idempotently generate missing core enrichment sections for a completed analysis (use when get_analysis reports readyForExport: false, then poll again). Optionally request bundled deep-only modules via `modules`: proofOfDemand (verified real-demand prospects; beta - results can be uneven, every quote links to its source), founderFit (founder-vs-plan underwriting, requires founderProfile), playbook (launch playbook), trends (on-demand Google Trends generation - the analysis pipeline never fetches Trends itself). Cap: one successful generation per module per report (409 MODULE_ALREADY_GENERATED on regen; failures are retryable). founderFit returns inline (up to ~90s); the others run async - poll get_analysis `modules` statuses.
export_analysis	Structured JSON export (schemaVersion 2) for one COMPLETED analysis: scores, verdict, risks, competitors, and — for deep reports — full sections, pivots, and citations. Call after readyForExport is true.
create_batch	Create up to 10 analysis runs in one batch. Idempotent on the batch clientRunId (replaying returns the existing batch). Poll with get_batch, then export with export_batch. Prefer scanType "starter" items unless deep scans are intentional (each deep item spends paid quota).
get_batch	Poll a batch by id. Returns per-item statuses. Items with readyForExport: false after completion need enrich_analysis on their run id.
export_batch	Structured JSON export (schemaVersion 2) for a completed batch. Includes counts.exported/omitted and an omittedItems list with the reason each incomplete item was skipped.