Hosted MCP server · #45 most used on Smithery · ✓ verified

Exa Search

exa

Fast, intelligent web search and web crawling. Get fresh information about libraries, APIs, and SDKs.

Backend & APIs Browser & web

Install ↓Smithery ↗Website ↗

Uses: 9.2k
Tools: 2
Runs: Hosted
Prompts: 1
Listed: 1.9y ago

Get started

Add it to your agent

npx -y @smithery/cli@latest install exa --client claude

Swap --client claude for cursor, vscode, windsurf or another client. The CLI asks for any required settings.

claude mcp add --transport http exa-search https://server.smithery.ai/exa/mcp

A hosted server: nothing to install. Run /mcp in Claude Code to sign in if it asks.

[mcp_servers.exa-search]
url = "https://server.smithery.ai/exa/mcp"

Add to ~/.codex/config.toml.

{
  "mcpServers": {
    "exa-search": {
      "url": "https://server.smithery.ai/exa/mcp"
    }
  }
}

Add to ~/.cursor/mcp.json.

{
  "servers": {
    "exa-search": {
      "type": "http",
      "url": "https://server.smithery.ai/exa/mcp"
    }
  }
}

Add to .vscode/mcp.json.

gemini mcp add --transport http exa-search https://server.smithery.ai/exa/mcp

Saved to .gemini/settings.json.

What it can do

2 tools

web_search_exa2 paramsSearch the web for any topic and get clean, ready-to-use content. Best for: Finding current information, news, facts, people, companies, …

Search the web for any topic and get clean, ready-to-use content. Best for: Finding current information, news, facts, people, companies, or answering questions about any topic. Returns: Clean text content from top search results. Query tips: describe the ideal page, not keywords. "blog post comparing React and Vue performance" not "React vs Vue". Use category:people / category:company to search through Linkedin profiles / companies respectively. If highlights are insufficient, follow up with web

Parameter	Type	Description
`query`	string	Natural language search query. Should be a semantically rich description of the ideal page, not just keywords. Optionally include category:<type> (company, people) to focus results — e.g. 'category:pe
`numResults`	number	Number of search results to return (default: 10).

web_fetch_exa2 paramsRead a webpage's full content as clean markdown. Use after web_search_exa when highlights are insufficient or to read any URL. Best for: …

Read a webpage's full content as clean markdown. Use after web_search_exa when highlights are insufficient or to read any URL. Best for: Extracting full content from known URLs. Batch multiple URLs in one call. Returns: Clean text content and metadata from the page(s).

Parameter	Type	Description
`urls`	array	URLs to read. Batch multiple URLs in one call.
`maxCharacters`	number	Maximum characters to extract per page (default: 3000)

Ready-made

Prompts

web_search_helpGet help with web search using Exa

Readable data

Resources

tools_listList of available Exa tools and their descriptions