Exa MCP Server

Connect AI assistants to Exa's search capabilities: web search, code search, and company research.

Full Documentation | npm Package | Get Your Exa API Key

Installation

Connect to Exa's hosted MCP server:

https://mcp.exa.ai/mcp

Get your API key

Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "exa": {
      "url": "https://mcp.exa.ai/mcp"
    }
  }
}

VS Code

Add to .vscode/mcp.json:

{
  "servers": {
    "exa": {
      "type": "http",
      "url": "https://mcp.exa.ai/mcp"
    }
  }
}

Claude Code

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

Claude Desktop

Exa is available as a native Claude Connector — no config files or terminal commands needed.

1. Open Claude Desktop Settings (or Customize) and go to Connectors
2. Search for Exa in the directory
3. Click + to add it

That's it! Claude will now have access to Exa's search tools.

Alternative: manual config

Add to your config file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "exa": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.exa.ai/mcp"]
    }
  }
}

Codex

codex mcp add exa --url https://mcp.exa.ai/mcp

OpenCode

Add to your opencode.json:

{
  "mcp": {
    "exa": {
      "type": "remote",
      "url": "https://mcp.exa.ai/mcp",
      "enabled": true
    }
  }
}

Antigravity

Open the MCP Store panel (from the "..." dropdown in the side panel), then add a custom server with:

https://mcp.exa.ai/mcp

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "exa": {
      "serverUrl": "https://mcp.exa.ai/mcp"
    }
  }
}

Zed

Add to your Zed settings:

{
  "context_servers": {
    "exa": {
      "url": "https://mcp.exa.ai/mcp"
    }
  }
}

Gemini CLI

Add to ~/.gemini/settings.json:

{
  "mcpServers": {
    "exa": {
      "httpUrl": "https://mcp.exa.ai/mcp"
    }
  }
}

v0 by Vercel

In v0, select Prompt Tools > Add MCP and enter:

https://mcp.exa.ai/mcp

Warp

Go to Settings > MCP Servers > Add MCP Server and add:

{
  "exa": {
    "url": "https://mcp.exa.ai/mcp"
  }
}

Kiro

Add to ~/.kiro/settings/mcp.json:

{
  "mcpServers": {
    "exa": {
      "url": "https://mcp.exa.ai/mcp"
    }
  }
}

Roo Code

Add to your Roo Code MCP config:

{
  "mcpServers": {
    "exa": {
      "type": "streamable-http",
      "url": "https://mcp.exa.ai/mcp"
    }
  }
}

LM Studio

Or add manually: open LM Studio, go to the Program tab, click Install > Edit mcp.json, and add:

{
  "exa": {
    "url": "https://mcp.exa.ai/mcp"
  }
}

Exa's tools will appear in the chat. Ask your model to search the web, fetch a page, or research a topic.

Replit

Go to Integrations > MCP Servers > Add MCP Server, then enter:

• Name: Exa
• URL: https://mcp.exa.ai/mcp

Or click here to install automatically.

Other Clients

For clients that support remote MCP:

{
  "mcpServers": {
    "exa": {
      "url": "https://mcp.exa.ai/mcp"
    }
  }
}

For clients that need mcp-remote:

{
  "mcpServers": {
    "exa": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.exa.ai/mcp"]
    }
  }
}

Via npm Package

Use the npm package with your API key. Get your API key.

{
  "mcpServers": {
    "exa": {
      "command": "npx",
      "args": ["-y", "exa-mcp-server"],
      "env": {
        "EXA_API_KEY": "your_api_key"
      }
    }
  }
}

Available Tools

Enabled by Default: | Tool | Description | | ---- | ----------- | | web_search_exa | Search the web for any topic and get clean, ready-to-use content | | web_fetch_exa | Get the full content of a specific webpage from a known URL |

Off by Default: | Tool | Description | | ---- | ----------- | | web_search_advanced_exa | Advanced web search with full control over filters, domains, dates, and content options |

Exa Agent Tools (optional, OAuth or API key required): | Tool | Description | | ---- | ----------- | | agent_create_run | Start an async Exa Agent run for multi-step research, list-building, enrichment, or structured output | | agent_wait_for_run | Poll an Agent run until terminal status or timeout | | agent_get_run_output | Retrieve completed text, structured output, grounding, usage, and cost | | agent_cancel_run | Cancel a queued or running Agent run |

Deprecated (still available for backwards compatibility):

Enable additional tools with the tools parameter:

https://mcp.exa.ai/mcp?exaApiKey=YOUR_KEY&tools=web_search_exa,web_search_advanced_exa,web_fetch_exa

If you want to use Exa Agent, enable the optional toolset like so:

https://mcp.exa.ai/mcp?tools=agent_tools

If you want both search and Exa Agent tools enabled:

https://mcp.exa.ai/mcp?tools=web_search_exa,web_fetch_exa,agent_tools

Agent Skills (Claude Skills)

Ready-to-use skills for Claude Code. Each skill teaches Claude how to use Exa search for a specific task. Copy the content inside a dropdown and paste it into Claude Code — it handles the rest.

Company Research

Copy the content below and paste it into Claude Code. It will set up the MCP connection and skill for you.

Step 1: Install or update Exa MCP

If Exa MCP already exists in your MCP configuration, either uninstall it first and install the new one, or update your existing MCP config with this endpoint. Run this command in your terminal:

claude mcp add --transport http exa "https://mcp.exa.ai/mcp?tools=web_search_advanced_exa"


Step 2: Add this Claude skill

---
name: company-research
description: Company research using Exa search. Finds company info, competitors, news, financials, LinkedIn profiles, builds company lists. Use when researching companies, doing competitor analysis, market research, or building company lists.
context: fork
---

# Company Research

## Tool Restriction (Critical)

ONLY use `web_search_advanced_exa`. Do NOT use `web_search_exa` or any other Exa tools.

## Token Isolation (Critical)

Never run Exa searches in main context. Always spawn Task agents:
- Agent runs Exa search internally
- Agent processes results using LLM intelligence
- Agent returns only distilled output (compact JSON or brief markdown)
- Main context stays clean regardless of search volume

## Dynamic Tuning

No hardcoded numResults. Tune to user intent:
- User says "a few" → 10-20
- User says "comprehensive" → 50-100
- User specifies number → match it
- Ambiguous? Ask: "How many companies would you like?"

## Query Variation

Exa returns different results for different phrasings. For coverage:
- Generate 2-3 query variations
- Run in parallel
- Merge and deduplicate

## Categories

Use appropriate Exa `category` depending on what you need:
- `company` → homepages, rich metadata (headcount, location, funding, revenue)
- `news` → press coverage, announcements
- `people` → LinkedIn profiles (public data)
- No category (`type: "auto"`) → general web results, deep dives, broader context

Start with `category: "company"` for discovery, then use other categories or no category for deeper research.

### Category-Specific Filter Restrictions

When using `category: "company"`, these parameters cause 400 errors:
- `includeDomains` / `excludeDomains`
- `startPublishedDate` / `endPublishedDate`
- `startCrawlDate` / `endCrawlDate`

When searching without a category (or with `news`), domain and date filters work fine.

**Universal restriction:** `includeText` and `excludeText` only support **single-item arrays**. Multi-item arrays cause 400 errors across all categories.

## LinkedIn

Public LinkedIn via Exa: `category: "people"`, no other filters.
Auth-required LinkedIn → use Claude in Chrome browser fallback.

## Browser Fallback

Auto-fallback to Claude in Chrome when:
- Exa returns insufficient results
- Content is auth-gated
- Dynamic pages need JavaScript

## Examples

### Discovery: find companies in a space
```
web_search_advanced_exa {
  "query": "AI infrastructure startups San Francisco",
  "category": "company",
  "numResults": 20,
  "type": "auto"
}
```

### Deep dive: research a specific company
```
web_search_advanced_exa {
  "query": "Anthropic funding rounds valuation 2024",
  "type": "deep",
  "numResults": 10,
  "includeDomains": ["techcrunch.com", "crunchbase.com", "bloomberg.com"]
}
```

### News coverage
```
web_search_advanced_exa {
  "query": "Anthropic AI safety",
  "category": "news",
  "numResults": 15,
  "startPublishedDate": "2024-01-01"
}
```

### LinkedIn profiles
```
web_search_advanced_exa {
  "query": "VP Engineering AI infrastructure",
  "category": "people",
  "numResults": 20
}
```

## Output Format

Return:
1) Results (structured list; one company per row)
2) Sources (URLs; 1-line relevance each)
3) Notes (uncertainty/conflicts)


Step 3: Ask User to Restart Claude Code

You should ask the user to restart Claude Code to have the config changes take effect.

Code Search

Copy the content below and paste it into Claude Code. It will set up the MCP connection and skill for you.

```` Step 1: Install or update Exa MCP

If Exa MCP already exists in your MCP configuration, either uninstall it first and install the new one, or update your existing MCP config with this endpoint. Run this command in your terminal:

claude mcp add --transport http exa "https://mcp.exa.ai/mcp?tools=web_search_exa"

Step 2: Add this Claude skill

name: code-search-exa description: Code context using Exa. Finds real snippets and docs from GitHub, StackOverflow, and technical docs. Use when searching for code examples, API syntax, library documentation, or debugging help. context: fork

Code Context (Exa)

Tool Restriction (Critical)

ONLY use web_search_exa. Do NOT use other Exa tools.

Token Isolation (Critical)

Never run Exa in main context. Always spawn Task agents: - Agent calls web_search_exa - Agent extracts the minimum viable snippet(s) + constraints - Agent deduplicates near-identical results (mirrors, forks, repeated StackOverflow answers) before presenting - Agent returns copyable snippets + brief explanation - Main context stays clean regardless of search volume

When to Use

Use this tool for ANY programming-related request: - API usage and syntax - SDK/library examples - config and setup patterns - framework "how to" questions - debugging when you need authoritative snippets

Query Writing Patterns (High Signal)

To reduce irrelevant results and cross-language noise: - Always include the programming language in the query. - Example: use "Go generics" instead of just "generics". - When applicable, also include framework + version (e.g., "Next.js 14", "React 19", "Python 3.12"). - Include exact identifiers (function/class names, config keys, error messages) when you have them.

Output Format (Recommended)

Return: 1) Best minimal working snippet(s) (keep it copy/paste friendly) 2) Notes on versio