Real human judgment as agent tools -- an AI agent can ask a question and get back a structured, schema-validated JSON answer from a real quality-scored human. 16 response types (yes/no, ratings, rankings, A/B tests, sentiment, image/video/audio review, voice/video/photo capture). Fully programmatic signup with a $5 free trial credit, no card required.
Lets an AI agent pull the user's own Douyin creator-backend work data — plays, likes, comments, shares, saves, 5-second completion rate and more — into a locally accumulating CSV plus a daily overview, with tools for status checks, fetching, merging, and retrospective analysis. Access is read-only to the user's own account, needs no third-party dependencies, and keeps all data on the local machine.
An MCP server that searches across the Internet Archive and Library of Congress at once, merging results while keeping each archive's differences. Provides tools to search inside texts, search catalogues, and retrieve item records, all read-only and without an API key.
Predicts the outcome of Dutch court cases dismissed, partly granted, or granted using a model trained on 609,715
rulings, with the outcome leakage measured and removed: 92% of Dutch judgment texts state the outcome verbatim, 0.1%
remains after the cut, giving 78.2% accuracy against a 43.7% majority baseline. The lekkage_check tool exposes that same
measurement so anyone can test a datase
Enables LLMs to search and retrieve exam problems, solutions, and answers from the СДАМ ГИА educational platform across multiple subjects. It supports fuzzy text matching, catalog browsing, and structured data retrieval to assist with academic study and test preparation.
An MCP server implementing the ROBINS-I V2 framework for risk-of-bias assessment in non-randomized studies, with deterministic algorithms and full provenance. It enables users to parse study documents, specify target trial results, answer signalling questions with evidence-bound quotes, and compute or override domain judgements.
Enables AI clients to analyze any company domain and determine its AI maturity tier (commercialized, deployed, declared, or none) with supporting evidence, via a single tool backed by an Apify actor.
MCP server that exposes the Storm cross-venue prediction-market intelligence API, enabling LLM clients to read canonical events, spreads, venue catalog, and alerts as native tool calls.
Free competitive pricing intelligence for SMB CPG brands. Check where any product price sits in its Amazon category, track pricing trends, and compare products — no NielsenIQ or SPINS subscription needed.
Remote MCP server for the UNESCO Institute for Statistics (UIS): ~5,000 indicators on education, science/R&D, culture and communication by country, region and year — hosted, nothing to install, no API key, with source URL, data release, retrieval timestamp and licence on every answer.
Academic peer-review (HAKEM), research-gap finding, journal recommender (1,214 venues with predatory flags), duplicate publication checker, and article writer tools from Science AI Journal. Free local FTS5 tools + LLM-backed tools that bill the caller's account.
Enables users to track a list of company domains and retrieve only the job-board changes since the previous run, including new, closed, and reposted postings with full descriptions, stable posting keys, and 30-day hiring velocity per company. It runs on Apify and exposes this through a single tool call.