qune-tech/ocds-mcp C MCP Server Active
German public procurement data (OCDS) — semantic search, tender matching with company profiles, and structured filtering.
186 MCP servers and agent skills in the Search & Data Extraction category, ranked by quality score.
German public procurement data (OCDS) — semantic search, tender matching with company profiles, and structured filtering.
MCP server for ScraperAPI web scraping with JavaScript rendering, geotargeting, premium proxies, and auto-parsing support.
Schema-validated document extraction with searchable workspace memory. Extract structured fields from PDFs, scans, images, and forms; AI agents can also search, filter, and query past extractions.
Official remote MCP server for Muumuu Domain (GMO Pepabo). Search and register domains, manage owned domains and contracts, and configure DNS records via natural language.
YouTube transcript extraction for AI agents. Clean text, timestamps, or structured JSON from any video. No API keys required. Install via `npx rippr-mcp`.
RSS feeds MCP server with 8 tools — fetch, filter, search, and manage RSS feeds by category or source. Zero config, no API keys required.
MCP server that fetches YouTube video transcripts and optionally summarizes them. Supports multiple transcript formats (text, JSON, SRT, WebVTT), multi-language retrieval, and flexible YouTube URL parsing.
Crawl websites into clean Markdown, search pages, and extract structured data with LLMs. Built-in MCP server for web research and RAG pipelines.
Multi-provider search broker with automatic fallback, RRF ranking, content extraction, and budget enforcement.
Self-contained SearXNG MCP server in Docker. 200+ search engines, 30+ categories, multi-page fanout, autocomplete, and engine discovery. Dual transport (HTTP + stdio), API key auth, and built-in SearXNG Web UI reverse proxy. Zero-install deploy.
MCP server for MinerU document parsing API. Parse PDFs, images, DOCX, and PPTX with OCR (109 languages), batch processing (200 docs), page ranges, and local file upload. 73% token reduction with structured output.
Keyless web access for AI agents: an escalating open-source unlocker (browser-fingerprint fetch → JS-render relay → stealth browser) reads bot-walled pages as clean Markdown, plus multi-provider web search with rank fusion, subtitles-first video transcripts, and page asset grabbing. No API keys; ships a reproducible benchmark.
Search GOV.UK content, retrieve full government pages, look up organisations, and resolve UK postcodes to local authorities. 5 read-only tools, no API keys required.
Pay-per-call agent APIs over x402 (USDC on Base): per-token LLM inference (Llama 3.1/Qwen/Mistral), per-second GPU/CPU compute, on-chain/DeFi + SEC-EDGAR + news data, and clean-Markdown/Cloudflare-stealth web scraping. Signed receipts, no signup — auto-claims a free-tier key. Install via `npx -y gate402-mcp`.
Google SERP search including web, images, news, maps, places, videos, and knowledge graph results via Ace Data Cloud API.
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.
Free capability-routed search and web reading for agents: GitHub, Crossref, Hacker News, Wikipedia, private SearXNG, and URL-to-Markdown, with live health diagnostics and no telemetry. Exposes `web_search`, `read_url`, and `search_status`.
MCP search and evidence tool for AI agents. Rewrites queries, zooms into source domains, and returns sourced answers with metrics.
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 `content_filter=high` by default. Install via `npx -y @hanoak/unsplash-mcp-server`.
Licensed, rights-cleared content for AI agents — discover, purchase, verify, and retrieve expert analysis with a verifiable license key per article, on-chain proof, and EU AI Act Article 53 attestation. The alternative to unlicensed scraping for RAG and AI search. `npx opedd-mcp`
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`.
Multi-provider web search with intelligent auto-routing (Serper, Tavily, Exa). Available via `uvx web-search-plus-mcp`.
Model Context Protocol Server for looking up company ethics information. Learn about the ethical and unethical actions of major companies.
Search 1M+ enriched job listings from 20,000+ companies. Filter by skills, salary, location, seniority, remote type, and more. Free — 500 calls/day, no signup required. Also available as a remote MCP server at `https://mcp.jobdatalake.com`.
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 `read_url`. Install via `npx -y skim-mcp`.
Resolves a company domain or name to its LinkedIn company URL with confidence scoring and firmographic metadata.
Live VR / AR / XR news, full-text VR.org originals, events calendar, headset deals and comparisons
Search, rank, and analyze GitHub developers for tech recruiting. Location/role/skill search over millions of ranked profiles with AI scoring and contact discovery. Install via `npx githunt-mcp` or use the hosted server at `https://mcp.githunt.ai/mcp`.
Japanese-web-native web fetching optimized for low target-site impact and token efficiency. Outline-first progressive disclosure, Shift_JIS/EUC-JP mojibake handling, PDF/CSV extraction, and polite crawling (robots.txt, rate limits, honest User-Agent). Install via `npx -y amenbo`.
Enriches a company domain into firmographics: employee band, industry, HQ, founded year, revenue estimate, logo, and description, with source provenance.
Search products and stores in nearby physical stores. Find what you need locally instead of waiting for delivery. Remote MCP server (Streamable HTTP, no API key required).
Search and discover rescue dogs from European and UK organizations with AI-powered personality matching and detailed profiles.
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.