Universal AI-driven comparison engine: ask in natural language, get a real-time comparison built from real, sourced data. Provably neutral (never pay-to-rank), traceable sources, multi-language and multi-country. Built for both humans and AI agents (MCP, JSON, Markdown).
Scored across 3 tools
Each tool serves a distinct purpose: search to find comparisons, get to retrieve details, and list categories for browsing. No overlap.
All tools use consistent verb_noun snake_case naming: get_comparison, list_categories, search_comparisons.
Three tools is minimal but adequate for a read-only comparison catalog. Slightly thin but still reasonable.
Covers search, retrieval, and category listing, but missing a way to list all comparisons within a category without a specific search query.
Fetch one full structured comparison (items with scores, sub-scores, per-criterion values, badges, sources, sourced/estimate flags, freshness). Neutral ranking, never paid. Data is localized to the requested lang/country.
Inputs: slug (required), lang, country.
List the top-level categories available for a market, with the number of comparisons in each.
Inputs: lang, country.
Search CompareFairly's catalog of neutral, sourced comparisons for a given market. Returns matching comparisons (title, slug, url, json_url, popularity). Use this first to find the exact slug, then call get_comparison.
Inputs: lang, limit, query, country.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Add one secure layer between your agents and this server.