MCP Servers

Tells AI agents how independently a claim is being reported: syndication-aware source counting (a wire story reprinted by 40 outlets counts as one origin), 0-1 confidence scores, and published error rates in-repo. Measures corroboration, not truth — no stance detection. Keyless, no accounts. Install: npx -y corroborate-mcp.

Japanese-web-native web fetching optimized for low target-site impact and token efficiency. Outline-first progressive disclosure, ShiftJIS/EUC-JP mojibake handling, PDF/CSV extraction, and polite crawling (robots.txt, rate limits, honest User-Agent). Install via npx -y amenbo.

Search the Feedbagel RSS catalog, follow feeds, and route new entries to webhooks.

Scans Google News and PR wires for a company's funding rounds, exec moves, product launches, and acquisitions, returned as deduplicated, dated events in flat Clay-ready JSON.

Resolves a company domain or name to its LinkedIn company URL with confidence scoring and firmographic metadata.

Enriches a company domain into firmographics: employee band, industry, HQ, founded year, revenue estimate, logo, and description, with source provenance.

Runs and manages its own local models, or uses your existing Ollama or LM Studio if you prefer. Indexes your files and code, crawls the websites you point it at, and answers with citations to the source.

Free multi-engine MCP search server — 8 free engines (DDG, Sogou, Bing, Baidu, Wikipedia, Startpage, Yandex, Mojeek), waterfall progressive search, multi-source verification, content enrichment, news search, language auto-detection, CLI. Zero API keys needed. npx agent-search-mcp

Chromium-free web content extraction in a single binary. Fetch, render, crawl, and screenshot powered by the Servo browser engine with a built-in MCP server.

Convert any URL into clean, agent-ready Markdown with structured metadata (title, byline, published date, language). Pay-per-use via x402 (USDC on Base) — no signup, no API keys. Single tool readurl. Install via npx -y skim-mcp.

Unsplash API server exposing 21 tools across photos, search, users, collections, topics, and stats. Ships Unsplash-guideline compliance built in — ready-to-use attribution with UTM parameters, a download-tracking tool, rate-limit surfacing, and contentfilter=high by default. Install via npx -y @hanoak/unsplash-mcp-server.

MCP server that lets AI agents search and extract data from major Chinese internet platforms including Taobao, JD, Xiaohongshu, Zhihu, Weibo, Bilibili, ZSXQ, Douban, and Dianping, with local-first cookie storage and CDP-assisted login.

Hosted MCP for structured public web data — 319 tools across search, maps, commerce, social, and finance, each returning clean JSON. Free 2,000 credits/mo.

Hacker News tools for AI agents: top stories by time window, category feeds (top/new/best/ask/show/job), comment threads, and full-text search via Algolia. No API key required.

Curated audio-news with a market-aware news signal. Search articles, fetch narrated audio, subscribe topic feeds, surface stories matched to actively traded Kalshi event contracts (CFTC-regulated; qualitative signal tags + link-out to Kalshi, never raw market data). 8 tools (7 free + 1 x402-paid over USDC on Base). Install via npx -y storyflo-mcp.

Verified ICD-10-CM medical code lookup, validation & reverse search — official descriptions, never guessed.

Real-time, ML-enriched news intelligence — urgency scoring, political lean & event clustering across 190+ countries.

Local-first, keyless web intelligence in one server: search, fetch, crawl, extract, cache, find-similar, and research. Multi-engine search with local ML reranking and a persistent SQLite cache, renders JS-heavy pages, and keeps everything on your machine. Install via npx wigolo init --non-interactive --agents=.

Build a searchable index from PDFs, EPUBs, and Word docs. Claude queries it via MCP and pulls grounded answers with exact page-and-section citations. Local-first, no cloud dependency.

Chemistry toolbox computed from authoritative data: molecular weight / molar mass of any formula (nested groups, isotope labels, propagated NIST uncertainties, percent composition), isotope-distribution mass spectra (m/z peaks for a given charge), and name⇆formula lookup with isomer resolution. Element masses from the NIST Atomic Weights and Isotopic Compositions database; offline and deterministic, with an optional on-by-default online fallback (PubChem/Wikidata/EPA CompTox) that can be disable

Semantic Scholar MCP server: 14 typed tools over 200M+ academic papers — search, paper/author retrieval, citation-graph traversal, and recommendations. uvx s2-mcp-server

Patent prior art search and startup IP intelligence for AI founders. Clone risk score, defensibility map, patentable features, competitor patent landscape — free analysis in ~2 minutes. Full IP Portfolio Package (6 documents) available for $99. pip install fittin-mcp

MCP server for patent search and prior art discovery powered by Google Patents public dataset on BigQuery. Tools: search patents, get full patent details with CPC codes and citations, fetch legal claims text. Free to use.

Natural-language patent and scientific literature search across 200M+ patents and 216M+ papers from 170+ jurisdictions, with semantic/BM25 search, structured filters, and record retrieval. Hosted Streamable HTTP endpoint and Dockerized stdio bridge; requires a free Patsnap API key.