MCP Directory

MCP servers that search the web

Give your AI live web search results with sources.

10 servers · Last updated June 17, 2026

TL;DR: These servers return fresh search results so your agent can answer with current information and cite sources, instead of relying on stale training data. They differ on index (general vs developer-focused), whether they return full page content or just snippets, and pricing model.

Bottom line: if you only try one, Firecrawl is the most popular, verified option for this (6,562★). 9 more compared below.

Compare 10 servers

ServerTransportAuthVerifiedStarsTools for this
FirecrawlLocal (stdio)API key6,562firecrawl_search
Exa SearchLocal (stdio)API key4,573web_search_exa, web_search_advanced_exa, company_research_exa +1
PerplexityLocal (stdio)API key2,299perplexity_search, perplexity_research
TavilyLocal (stdio)API key2,100tavily-search
Apify ActorsLocal (stdio)API key1,336search-actors, search-apify-docs
DuckDuckGo SearchLocal (stdio)No auth1,236search
Brave SearchLocal (stdio)API key1,179brave_web_search, brave_local_search, brave_image_search +3
SearXNGLocal (stdio)No auth896searxng_web_search, searxng_search_suggestions
Jina AI Reader & SearchRemote (HTTP)API key730search_web, search_images, search_arxiv +1
Kagi SearchLocal (stdio)API key417kagi_search_fetch

The servers

Official Firecrawl MCP server — scrape, crawl, map, search, and structured extraction for any LLM client.

firecrawl_search

Exa's neural web search and crawling MCP server — runs locally via npx or as a hosted remote endpoint.

web_search_exaweb_search_advanced_exacompany_research_exadeep_researcher_start / deep_researcher_check

Official Perplexity MCP server — web search, ask, deep research, and reasoning via Sonar models.

perplexity_searchperplexity_research

Production-ready MCP server for real-time web search, content extraction, site mapping, and crawling.

tavily-search

Official Apify MCP server — search and scrape the web via thousands of ready-made Actors; local or remote.

search-actorssearch-apify-docs

Popular no-API-key MCP server for DuckDuckGo web search plus page fetching and parsing.

search

Official Brave Search MCP server: web, local, image, video, news search and AI summarization.

brave_web_searchbrave_local_searchbrave_image_searchbrave_video_searchbrave_news_searchbrave_place_search

Private metasearch via your own SearXNG instance — popular community MCP server for self-hosted search.

searxng_web_searchsearxng_search_suggestions

Official Jina AI remote MCP server — read web pages as Markdown and run grounded web search over HTTP.

search_websearch_imagessearch_arxivparallel_search_web

Official Kagi MCP server (Python/uvx) — privacy-first web search and URL/video summarization.

kagi_search_fetch

Use these in a stack

FAQ

Which web-search MCP is best for AI agents?

For citations and clean snippets, API-first engines (Brave, Tavily, Exa) work well; Exa skews developer/semantic. Compare them head-to-head on the directory before committing.

Do these need an API key?

Most do — you'll provision a key from the search provider and drop it in the config. A few self-hosted options (SearXNG) avoid that.

Other capabilities