Web Search MCP servers

Deep research via the OpenAI Responses API or Open Deep Research (smolagents), with web search and code interpreter support.

Search across DuckDuckGo, Sogou, Bing, Baidu, Wikipedia, Startpage, Yandex and Mojeek with waterfall search, multi-source verification and news search.

Capture website screenshots, tiling full pages into 1072x1072 chunks for Claude Vision, with configurable viewports and wait strategies for dynamic content.

Crawl documentation sites into local Markdown or JSONL corpora and serve them with offline BM25 search, page reads, freshness checks and crawl diffs.

Expose OpenAI's built-in web search tool.

Lightning-Fast, High-Accuracy Deep Research Agent 8–10x faster Greater depth & accuracy Unlimited parallel runs

Self-hosted perception server: local bilingual ASR, vision, cross-lingual search, credentialed login-walled sources and a persistent relation graph.

Naver Search API integration: blog, news and shopping search plus DataLab analytics.

Access computational knowledge and data via the Wolfram Alpha API.

PDF extraction router that classifies each page and routes it to PyMuPDF, Docling, OCR or an LLM fallback, re-extracting pages with low confidence scores.

Natural-language patent and scientific literature search via Patsnap: semantic and BM25 search, structured filters and record retrieval.

Query network asset information from ZoomEye.

Web search using the Microsoft Bing Search API.

Perplexity AI MCP server — browser automation for search, reasoning, research, and compute. Not affiliated with Perplexity AI, Inc.

Search Hacker News, get top stories and more.

Local, offline full-text code search for coding agents using a trigram index over large codebases.

MCP server that lets AI assistants control LinkedIn accounts and retrieve real-time data with Linked API.

Web search via Google, Brave, Serper, SearXNG and SearchAPI.io, multi-tier content extraction, academic and patent search, and multi-source research.

Search job listings with filters for date, keywords, remote work options and more.

Research workspace for Zotero, Obsidian and NotebookLM: search arXiv, Semantic Scholar, PubMed and Crossref, ingest into Zotero, sync notes and verify briefs.

Index files, code and crawled websites and answer with source citations, using its own local models or an existing Ollama or LM Studio setup.

Check domain availability across many TLDs with DNS and WHOIS verification, bulk checking and name suggestions.

Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching

Take screenshots of webpages to use as feedback during UI development.

Zotero integration: hybrid search, PDF passages with page locators, CSL bibliographies, add by DOI, group libraries and writes including PDF annotations.

Search and extract data from Chinese platforms including Taobao, JD, Xiaohongshu, Zhihu, Weibo, Bilibili, Douban and Dianping, with local cookie storage.

Extract typed, schema-defined records from any document and query them in natural language like a database.

MCP server for siGit (sigit.si): browse repos, search code, manage PRs/issues, web search.

Bridge Claude Code with Perplexity Comet for autonomous browsing and tab management

DigestSEO GEO tracker: measure brand citations and visibility across ChatGPT, Claude, Perplexity, Gemini and Google AI Overviews.

Search and retrieve web crawler data from WARC, wget, Katana, SiteOne and InterroBot crawls.

Web scraping tools with Chromium JS rendering, rotating proxies, and AI question answering.

Topics gaining momentum before they peak. Trend volume and growth signals. Free key at trendsmcp.ai

Real-time web search and premium data from media brands via Dappier: news, financial markets, sports, entertainment, weather and more.

Kagi search and summarization without API access, authenticated with a Kagi session token.

Pay-per-call x402 tools and skill packs (headless browser, web search, OCR, wallet-keyed memory), plus a router that finds the cheapest healthy tool.

Search Baseline status using the Web Platform API.

Official MCP server for OpenWeb Ninja APIs - 40+ real-time web data and SERP APIs as MCP tools

MCP server providing Google Search, web scraping, and multi-source research tools for AI assistants

Real-time world news: events clustered from many sources, classified by topic and geography and ranked by importance.

Geocoding via Nominatim, ArcGIS and Bing.

Scrape Google search results with SERP data, ads, and knowledge panels

Query search analytics, manage sitemaps, and inspect site URLs and status

Search the web, generate AI responses, and create embeddings with real-time information

Transcribe YouTube videos to text using yt-dlp for audio and OpenAI Whisper for transcription, with chunked output for long videos.

MCP server for iFlow Search web search, image search, and URL fetch tools.

Access Dumpling AI's data, web scraping and document conversion APIs.

Unsplash photo search, random photos and download tracking, with ready-to-use attribution text and HTML for each photo.