Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Exa approached search from the opposite direction to Google: instead of ranking pages for humans to click, it built a neural index designed for machines to consume. Queries match on meaning rather than keywords, and results come back with actual page content — not just links — formatted for a model to use immediately. Its MCP server is the cleanest way into that index.
The semantic matching changes what you can ask. "Startups building open-source alternatives to Datadog" is a terrible keyword query and a great Exa query — it describes the kind of thing you want, and the index finds pages that are that kind of thing. This makes Exa disproportionately good for research tasks: competitive landscapes, finding companies or people matching a profile, chasing down writing on a niche topic.
The server ships focused variants beyond plain web_search_exa: company research, LinkedIn search, crawling a specific URL, and a deep researcher mode where an Exa-side agent researches a question across many sources and returns a structured report. For developers, Exa's separate exa-code context tool searches billions of GitHub repos, docs pages and Stack Overflow posts to ground coding answers — a distinct angle on the anti-hallucination problem Context7 attacks via official docs.
It's remote-first (mcp.exa.ai) with an npm local option, and free-tier keys make it cheap to trial. Sensible mental model: Brave for "give me today's links", Exa for "find me the right sources and hand them to my model pre-chewed."
deep_researcher_start hands back a task ID, and the answer arrives via check minutes later, so don't design a flow that expects it in the same turn.Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Find things by description — 'companies doing X', 'papers arguing Y' — where keywords fail.
Company and people research assembled from live web data.
Delegate a question to the deep researcher and get back a synthesized, sourced report.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| web_search_exa | Semantic web search returning content, not just links |
| company_research | Research a company across the web |
| linkedin_search | Search LinkedIn profiles and companies |
| crawling | Fetch content from a specific URL |
| deep_researcher_start / check | Kick off and collect an agentic multi-source research report |
claude mcp add --transport http exa "https://mcp.exa.ai/mcp?exaApiKey=your-exa-key"An Exa API key (free tier available). Remote endpoint needs no local install.
| Variable | Description | Required |
|---|---|---|
| EXA_API_KEY | API key from dashboard.exa.ai (free tier available) | Yes |
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
Ask Claude, ChatGPT or Cursor "why did our clicks drop last month?" or "which keywords does our competitor rank for that we don't?" and it answers from real data instead of guessing.
Web search, scraping, RAG answers with citations, and translation as MCP tools.
Unified social scraper MCP — profiles, posts, videos across ~40 platforms via Streamable HTTP.
Eval-backed tool discovery for AI agents, on the auxiliar.ai web-access gateway — one API key for 24 search, scraping, browser-automation and voice APIs, upstream keys injected server-side, usage at…