# exa

Connects AI assistants to Exa for web searches, markdown content extraction, and multi-step online research.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 5163
- Author: exa-labs
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/exa-labs/exa-mcp-server
- Updated: 2026-10-19
- HTML: https://affpapa.org/en/nevibecode/mcp/exa

## What it does

The server runs as a hosted endpoint at `https://mcp.exa.ai/mcp` without needing a local build. By default, it exposes two tools: `web_search_exa` for general search and `web_fetch_exa` to pull clean markdown directly from specified URLs.

You can enable advanced options like `web_search_advanced_exa` and `agent_run` by appending a `tools` query parameter to the URL. Note that setting this parameter overwrites default tools completely, so you must include all required handlers explicitly. Running `agent_run` requires OAuth or an Exa API key.

## Requirements
- Remote server: `https://mcp.exa.ai/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http exa https://mcp.exa.ai/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add exa --url https://mcp.exa.ai/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "exa": {
            "url": "https://mcp.exa.ai/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "exa": {
            "type": "http",
            "url": "https://mcp.exa.ai/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http exa https://mcp.exa.ai/mcp
```

## When to use it
- find current web sources and documentation inside agent sessions
- fetch full webpage content converted into clean markdown
- run multi-step web investigations and list enrichment
- filter search results by domains, dates, and summaries

## Example prompts
- Search the web for recent library changes using `web_search_exa`
- Fetch this documentation URL as clean markdown
- Run a research task with `agent_run` to gather structured company data

## Similar
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [AIHawk](https://affpapa.org/en/nevibecode/mcp/aihawk.md) — MCP server · ★ 32221
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23263
- [SeleniumBase MCP](https://affpapa.org/en/nevibecode/mcp/seleniumbase-mcp.md) — MCP server · ★ 13169
- [Robin: AI-Powered Dark Web OSINT](https://affpapa.org/en/nevibecode/mcp/robin-ai-powered-dark-web-osint.md) — MCP server · ★ 7658

From the same set: [exa-labs/exa-mcp-server](https://affpapa.org/en/nevibecode/by/exa-labs/exa-mcp-server.md) — 2 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md