MCP server
Exa MCP server
Exa's official hosted MCP server gives AI search built for AI use, page fetching, advanced filters and a research agent.
- Official server
- Search and web
At a glance
- Maintained by
- Exa
- Tools exposed
- 4 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
Exa is a search engine designed for AI applications. Instead of a page of links for people, it returns results and content shaped for language models. Its official MCP server is hosted by Exa and offers web search, page fetching, an advanced search with filters and an agent tool that runs longer research tasks.
That makes it well suited to research assistants, where the goal is not a list of links but a well-sourced answer or a set of relevant documents.
Exa allows limited anonymous use, so you can try it without a key. For real use, an API key or sign-in gives higher limits and access to the research agent tool. All tools read from the web, and none change anything.
Research agents can run many searches for one question, which adds cost and time. We set clear limits on how much each task may spend and ask for sources on every claim. The results are a starting point for a person to review, not a final answer.
Use cases
Best business use cases
Deep research
Competitor scans
Technical lookups
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Read-only web search and fetch.
-
web_search_exaSearches the web and returns clean content. On by default.
-
web_fetch_exaReads full page content as markdown from URLs. On by default.
-
web_search_advanced_exaSearch with domain, date and other filters. Opt in.
-
agent_runRuns an Exa Agent for multi-step research and structured output. Needs auth.
Workflows
Example workflows
Market brief
-
1
A manager asks for a brief on a new market.
-
2
The assistant runs advanced searches with date filters.
-
3
It fetches the most relevant pages.
-
4
It writes a brief with sources.
-
5
The manager reviews and edits.
Find look-alike companies
-
1
Describe your best customers.
-
2
The assistant searches for similar companies.
-
3
It returns a list with websites.
-
4
It notes why each one matches.
-
5
Sales reviews the list before outreach.
Prompts
Example prompts
“Find recent articles on AI adoption in logistics companies, from the last six months, with sources.”
“List ten companies similar to our best customer, with a reason for each.”
“Fetch this page and summarize the pricing section.”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Desktop: claude_desktop_config.json
{
"mcpServers": {
"exa": {
"type": "streamable-http",
"url": "https://mcp.exa.ai/mcp"
}
}
}Claude Code: terminal
claude mcp add --transport http exa https://mcp.exa.ai/mcp- Hosted server: https://mcp.exa.ai/mcp (optional ?tools= and exaApiKey params, or x-api-key header).
- Local server: npm: exa-mcp-server.
- Needs: None for rate-limited anonymous use; Exa API key (exaApiKey param or x-api-key header) or OAuth for higher limits and agent_run.
Security
Security considerations
-
Untrusted content
Web pages can contain text written to mislead an AI. Treat results as data, not instructions.
-
Protect the API key
Store the key outside version control and rotate it if it leaks.
-
Watch usage
Searches are billed or rate limited. Set limits and monitor use.
-
Check sources
Ask for sources and check a sample of answers by hand.
Related servers
Servers that pair well with it
Brave Search
Brave's official MCP server gives AI live web, news, image, video and local search from Brave's own independent index.
Tavily
Tavily's official MCP server gives AI web search, content extraction, site mapping and crawling, all built for AI use.
Perplexity
Perplexity's official MCP server lets AI search the web, ask questions with cited answers, run deeper research and reason over results.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- AI agents AI that takes actions in your systems, such as qualifying leads or processing requests, with people checking the results.
- AI Product Development AI agents, knowledge assistants, copilots and document automation built into the way your team already works.
Solutions
View all solutions- AI sales research agent Short, sourced briefings on each prospect before a call, drafted by an AI agent from public information and your CRM.
- Price monitoring Collect competitor prices automatically, match them to your products and alert you when something changes.
- AI lead qualification Score, research and route every new inquiry so your team talks to the best leads first.
- Internal help desk assistant An assistant in Slack or Teams that answers policy and how-to questions from your handbooks and opens tickets when needed.
- Compliance tracking Track filing deadlines, licenses and obligations in one place, with reminders and AI summaries of relevant rule changes.
- Knowledge assistant (RAG) Ask a question in plain words and get an answer from your own documents, with links to the sources.
Industries
View all industriesGuides and articles
View all guides and articles- What are AI agents and how do businesses use them? What AI agents are, real business uses, the controls they need and how to start with one safely.
- What is the Model Context Protocol? A business guide to MCP: what it is, how MCP servers work, who supports it and how to start using it.
- How to build an AI workflow with MCP servers Plan, connect and test an AI workflow that uses MCP servers, from a single task to a reliable process.
- AI chatbot vs AI agent What separates a chatbot that answers from an agent that acts, and when you need each.
AI models
View all ai models- Claude Fable 5.1 The top tier of the Claude family, for the most demanding reasoning and long-horizon agent work, priced above Opus.
- Claude Opus 5.5 Anthropic's recommended starting point for most serious work: long-running agentic coding and knowledge work, with a 1M token context window.
- GPT-6 Astra OpenAI's most capable model, built for the hardest end-to-end work: complex reasoning, coding, computer use and research.
- DeepSeek V4 Pro DeepSeek's model for demanding reasoning and agent work, with thinking effort levels, tool calling, JSON output and a 1 million token window.
- Grok 4.7 xAI's current flagship for coding, agent tasks and knowledge work, with image input, tool calling, structured outputs, reasoning effort levels and a 500K window.
- Reasoning Models that think through multi-step problems before answering: analysis, planning, math, complex documents and agent work.
Glossary terms
View all glossary terms- AI agent An AI agent is software that uses a language model to plan steps, call tools and act toward a goal, instead of only answering one question.
- RAG RAG, or retrieval-augmented generation, is a method where an AI system first finds relevant passages in your documents, then answers using only those passages.
- MCP server An MCP server is a program or hosted service that exposes a system's data and actions as tools that AI assistants can use through the Model Context Protocol.
- Model Context Protocol The Model Context Protocol, or MCP, is an open standard for connecting AI assistants to external tools and data in a consistent way.
- Tool calling Tool calling is when an AI model asks the application to run a tool, such as a search or database lookup, and then uses the result in its answer.
- Chatbot A chatbot is software that holds a conversation with people through text or voice, answering questions or completing simple tasks.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
Yes. It is hosted and maintained by Exa.
Limited anonymous use works. A key or sign-in gives higher limits and the research agent.
It is built for AI applications and returns results and content shaped for language models.