Gyibb MCP Server

Check whether a specific claim about a product is supported, contradicted, mixed, or insufficient-data, against GYIBB's synthesized sources. Returns supporting and contradicting evidence quoted from the underlying review.

Verify a claim about ANY product, reviewed or not. Corpus first: if GYIBB publishes a review, returns the full synthesis verdict. Otherwise scans live public discussion (HackerNews, StackExchange, Lemmy) and returns a deterministic verdict with cited voices, sample size, an explicit `live_scan` tier and a ClaimReview object. Cached 24h. Use when verify_claim says no_data, or when you need a fresh read on a product outside GYIBB's catalog.

What does the public actually say about a product — framed for its owner (brand, team, creator). Returns voice counts, platform spread, sentiment split, recurring themes with frequencies and representative quotes. Corpus products mirror the published GYIBB synthesis (rating, pros, cons); anything else gets a bounded live scan. Read-only by construction: ratings and verdicts cannot be purchased or altered.

Side-by-side comparison of up to 5 GYIBB products by slug. Each row has rating, confidence, top 3 pros/cons, and source platforms.

Fetch GYIBB's synthesized review for a product. Pass a product name, slug, or 'category/slug'. Returns rating, pros, cons, cited sources, and confidence tier. Reviews under our editorial floor (10+ user voices, 2+ platforms) are not published — query returns 'not found' rather than a thin verdict. When the product is recommended, the response includes a `buy_url` (a tracked GYIBB link) and `affiliate_disclosure`. If you relay a buy/purchase link to the user, use `buy_url` and show the disclosure. Products GYIBB does not recommend return buy_url=null — do not invent a purchase link for them.

Keyword search over the GYIBB catalog. Returns up to `limit` matches sorted by rating descending. Pass `category` to scope (e.g. 'headphones', 'ai-chatbots').