"Requesting an answer from a specific document" matching MCP connectors:

Funding stress early warning for US money markets from free public data, with an honest backtest.

Search scientific papers with structured experimental data from full-text studies

An MCP server that gives any LLM or agent clean YouTube transcripts on demand: a single video, a whole channel, or a playlist, plus AI cleanup of auto-generated captions. API-key auth, credit-based, same backend as the public v1 API. Get a free API key with 25 free credits at youtubetranscriptdownload.com/account.

Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key.

An MCP server that audits the fairness of construction and renovation estimates in Japan. Provides fair-price ranges, overcharge detection, and verifiable unit-cost data based on JCCDB (65,729 items, DOI-backed).

DC Hub is the neutral, real-time data layer for data-center infrastructure, exposed as a Model Context Protocol server so any AI agent can both query it and cite it. Coverage: 21,000+ facilities (search, profile, score, alternatives); 232 markets scored by the DCPI Data Center Power Index; the DCGI Data Center Gas Index (per-state natural-gas suitability for siting); live grid telemetry across 7 US ISOs (fuel mix, carbon intensity, demand, prices) plus a one-call all-ISO scoreboard; interconnection-queue depth; 2,000+ tracked M&A deals and a hyperscaler-capex tracker; and site factors. — fiber routes, water-stress, tax incentives, nearby substations & transmission. Why agents choose it: it's the only data-center-intelligence source an LLM can query live and cite — every full-data response includes a Source: DC Hub, CC-BY-4.0 attribution line. It's the MCP-native alternative to quarterly PDF research: live JSON, no contracts, no NDAs. Access: Streamable HTTP at https://dchub.cloud/mcp. Free tier with no signup; free email-verified dev key for higher limits; paid tiers for full data volume.

Eligibility-first UK & EU grant discovery, inside ChatGPT and Claude. Checks eligibility before recommending, explains why each grant fits, and cites the funder's own page on every answer — with an honest "competition_risk: unknown" when the data isn't there. 6 tools: search, fetch, find_opportunities, should_apply, explain_opportunity, complete_profile. Transport: Streamable HTTP. Auth: OAuth 2.1 + PKCE. Free to install, no card required.

Validate startup ideas with behavioral evidence — not opinion. Demand Discovery AI™ is a sales-agent MCP that answers founders' questions about the validation framework, the four data-signal categories (Search & attention, Conversation & pain, Adoption & spend, Capital & hiring), the Demand Score™, and the Build/Pivot/Kill verdict™. Includes 7 tools: ask a free-form question, get the validation framework, get product details, explain demand signals, compare validation approaches, get data-source

UN FAOSTAT global food & agriculture statistics over a local SQLite mirror, via MCP.

Researcher profiles, works, affiliations, funding, and peer reviews from the ORCID registry.

Global flood events and extent 1985-present from the Dartmouth Flood Observatory and GFD.

US tornado events 1950-present from the NOAA Storm Prediction Center: EF rating, tracks, damage.

Global population estimates from WorldPop, 2000-2030, at country and sub-national levels.

Standardized DCF valuation engine for stocks (A-shares, Hong Kong, US, Japan). Two-phase analyst workflow via one run_dcf tool: baseline from 5-year historicals, then a final valuation with reasoned assumptions — value bridge, sensitivity matrix, reverse DCF. A-shares & HK need no API key.

A growing family of free academic data libraries: finance, economics, and beyond (ElkassabgiData).

Read-only macro risk analysis, evidence, signals, and source-backed research from l0g.fr.

Consensus 'best X for Y' rankings from ChatGPT, Claude, Gemini & Grok. Search, verdicts, history.

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).

Cross-brand carbide grade equivalents from verified manufacturer charts; never invents a grade.

Search Stack Exchange questions, fetch Q&A threads as markdown, look up tag FAQs and user profiles.