186 MCP servers and agent skills in the Search & Data Extraction category, ranked by quality score.
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Official Elasticsearch MCP server — query and explore Elasticsearch indices from AI agents.
fastCRW — open-source (AGPL-3.0), self-hostable Rust web crawler & search API for AI agents. Tools: `scrape`, `crawl`, `map`, and SearXNG-backed `search`. Single ~6MB static binary; reproducible 1K-URL benchmarks faster than hosted alternatives. Hosted MCP at [fastcrw.com/mcp](https://fastcrw.com/mcp) (Streamable HTTP, OAuth) or self-host.
MCP server that provides [AgentQL](https://agentql.com)'s data extraction capabilities.
MCP server that lets AI assistants control LinkedIn accounts and retrieve real-time data.
Crawl, embed, chunk, search, and retrieve information from datasets through [Trieve](https://trieve.ai)
Best people search engine that reduces the time spent on talent discovery
Web scraping for AI agents: one auto tool walks a cost-aware ladder (direct → rotating proxy → full browser), solving anti-bot challenges and reporting which rung delivered and what it cost. Pay-per-success, EU-hosted, free tier. [](https://glama.ai/mcp/servers/fouradata/mcp)
Interact with [WebScraping.ai](https://webscraping.ai) for web data extraction and scraping.
Official MinerU document parsing MCP ([mineru-open-mcp](https://pypi.org/project/mineru-open-mcp/) on PyPI). Converts PDFs, doc/docx/ppt/pptx, images, and spreadsheets to Markdown via the [MinerU](https://mineru.net) API; free Flash mode without an API key (about 20 pages per file); optional `MINERU_API_TOKEN` for higher limits.
Web search that returns extracted, answer-ready page content (url, title, date, text) instead of links. A Tavily alternative: same speed, 20.2% fewer tokens, higher answer quality (60.7% of decided duels) on a public replayable benchmark. One tool with automatic localization and an optional synthesized answer. Hosted Streamable HTTP at `https://mcp.serpdive.com`, or run `npx -y serpdive-mcp`.
Lightning-Fast, High-Accuracy Deep Research Agent
Live web search and clean-markdown page fetch over the Keenable web index. Two tools: `search_web_pages`, `fetch_page_content`. Keyless by default (1,000 req/hour); an optional API key lifts the cap. Hosted Streamable HTTP at `https://api.keenable.ai/mcp`, or run `npx -y @keenable/mcp`.
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.
Extract timestamped YouTube transcripts, plus search, video metadata, and related-video tools for Claude, Cursor, Windsurf, and AI agents.
The Driflyte MCP Server exposes tools that allow AI assistants to query and retrieve topic-specific knowledge from recursively crawled and indexed web pages.
Official MCP server for managing Searchcraft clusters, creating a search index, generating an index dynamically given a data file and for easily importing data into a search index given a feed or local json file.
Official MCP server for [Forge](https://voxell.ai), Voxell's hosted text-embedding API. Generate vector embeddings (turbo 1024d, pro 2560d, ultra 4096d; Matryoshka truncation) for semantic search and RAG. `npx -y @voxell/forge-mcp`
Complete product and pricing data solution for AI assistants. Search for products by barcode/ASIN/URL, access detailed product metadata, access comprehensive pricing data from thousands of retailers, view and track price history, and more.
Access data, web scraping, and document conversion APIs by [Dumpling AI](https://www.dumplingai.com/)