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.
Tracks buying and momentum signals for companies, such as funding rounds, senior hires, office openings, customer wins, and partnerships, with each event carrying its date.
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.
A keyless MCP server that lets agents search YouTube across multiple languages and queries, pull transcript highlights, ranges or query-matched passages, fetch real video frames, comments, chapters and channel outlier scores, all without an API key, OAuth or cookies. It also ships a research skill that plans multi-language queries, fans out to subagents, spot-checks quotes and reports coverage.
Enables federated multi-source research by fanning out queries across web, community, and social sources, deduplicating and interleaving results, and storing a persistent corpus for cross-checking.
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.
Read any public web page, or up to 20 in one batch, as a clean AIDocument: Markdown plus title, description, structure, and provenance, with navigation and boilerplate stripped. Reads are served through Lyrenth's own independently built web index, so each costs a fraction of the tokens of raw HTML and is origin-friendly. A third tool reports your plan and how many reads you have used.
Enables analyzing why a stock moved over a past window by running independent technical, company-news, and macro reads and reconciling them into verdicts and a narrative.
Tracks a company's long-form publication cadence per month and trend (accelerating, steady, declining, dormant) from a given domain. Provides detailed metrics like post counts, trend percentage change, formats detected, and reliability flags.
Enables coding agents to query AI model API prices, including historical point-in-time lookups with cited sources, using a bundled dated dataset and requiring no API keys.
Enables searching live job postings, aggregating labour-market slices, and reporting how long listings have been open, with filters for titles, location, salary, and more.
MCP server providing U.S. college ROI data (30-year NPV, major ROI, best-value rankings, and out-of-state tuition penalty) by wrapping a free, keyless API.
Pulls enterprise counts by NACE Rev.2 activity and size class from Eurostat and buckets them into SME and 250+ categories for the DTM TAM model, with tools to fill TAM spreadsheets directly.
Enables AI clients to search, read, and accurately quote public-domain books from Project Gutenberg, with chapter detection and stable line numbers for citation. Its quote_check tool verifies whether a quotation actually appears in a book and reports how faithful the copy is.
Evidence-based supplement recommendation MCP server covering 17 supplements and 40+ conditions with medication interaction checking and form quality classification.
YouTube outlier research on your own free Data API key. It ranks a channel's uploads by their multiple against that channel's own baseline, with Shorts and long-form scored separately, compares several channels at once, and expands a niche from a seed channel.
Provides an LLM agent with extreme value statistics tools for tail risk analysis, including peaks-over-threshold GPD fitting, VaR and Expected Shortfall estimation, return levels, threshold-stability diagnostics, and out-of-sample VaR backtesting.
Serves citable mechanical-engineering reference data — ISO 286 limits and fits, ISO 2768 general tolerances, typical material properties, and published process feasibility limits — as queryable tools for an MCP host. It reports only what the standards specify, refusing out-of-scope or unverifiable values with a stated reason instead of approximating.
MCP server that lets AI assistants like Claude Code and Codex drive the co-scientist engine to generate, review, rank, and evolve scientific hypotheses via an Elo tournament.
Real-time SEC Form 4 insider trading data — transactions with post-trade returns, cluster-buy signals, Form 144 early warnings, and 13F institutional holdings. 27 tools + 6 research prompts; free tier available.
Simulate hundreds of AI agents to predict how communities react to events and policies. Upload any document (PDF, Markdown, text) and DeepMiro spawns a diverse swarm of AI agents that debate, share, and form opinions — then delivers a calibrated prediction report. Free and open-source.
Most trading signals are noise. AlphaAssay puts them on trial — deflated Sharpe, out-of-sample, leakage forensics — and returns signed pass/fail verdicts anyone can verify. Methodology audits, not investment advice.
Enables querying a brand's visibility in AI assistant answers, including competitor presence, tracked prompts, and the answers and sources behind the metrics.