exa-mcp-server
byexa-labs· 1 MCP server
Connect AI assistants to Exa's search capabilities: web search, code search, and company research.
How to install exa-mcp-server?
exa-labs/exa-mcp-server
$git clone https://github.com/exa-labs/exa-mcp-serverInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install exa-mcp-server by running `git clone https://github.com/exa-labs/exa-mcp-server`, then use it for the current task and follow its documentation at https://github.com/exa-labs/exa-mcp-server.
README.md
| 1 | # Exa MCP Server |
| 2 | |
| 3 | [](https://cursor.com/en/install-mcp?name=exa&config=eyJuYW1lIjoiZXhhIiwidHlwZSI6Imh0dHAiLCJ1cmwiOiJodHRwczovL21jcC5leGEuYWkvbWNwIn0=) |
| 4 | [](https://vscode.dev/redirect/mcp/install?name=exa&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.exa.ai%2Fmcp%22%7D) |
| 5 | [](https://www.npmjs.com/package/exa-mcp-server) |
| 6 | |
| 7 | Connect AI assistants to Exa's search capabilities: web search, code search, and company research. |
| 8 | |
| 9 | **[Full Documentation](https://docs.exa.ai/reference/exa-mcp)** | **[npm Package](https://www.npmjs.com/package/exa-mcp-server)** | **[Get Your Exa API Key](https://dashboard.exa.ai/api-keys)** |
| 10 | |
| 11 | ## Installation |
| 12 | |
| 13 | Connect to Exa's hosted MCP server: |
| 14 | |
| 15 | ``` |
| 16 | https://mcp.exa.ai/mcp |
| 17 | ``` |
| 18 | |
| 19 | [Get your API key](https://dashboard.exa.ai/api-keys) |
| 20 | |
| 21 | <details> |
| 22 | <summary><b>Cursor</b></summary> |
| 23 | |
| 24 | Add to `~/.cursor/mcp.json`: |
| 25 | |
| 26 | ```json |
| 27 | { |
| 28 | "mcpServers": { |
| 29 | "exa": { |
| 30 | "url": "https://mcp.exa.ai/mcp" |
| 31 | } |
| 32 | } |
| 33 | } |
| 34 | ``` |
| 35 | </details> |
| 36 | |
| 37 | <details> |
| 38 | <summary><b>VS Code</b></summary> |
| 39 | |
| 40 | Add to `.vscode/mcp.json`: |
| 41 | |
| 42 | ```json |
| 43 | { |
| 44 | "servers": { |
| 45 | "exa": { |
| 46 | "type": "http", |
| 47 | "url": "https://mcp.exa.ai/mcp" |
| 48 | } |
| 49 | } |
| 50 | } |
| 51 | ``` |
| 52 | </details> |
| 53 | |
| 54 | <details> |
| 55 | <summary><b>Claude Code</b></summary> |
| 56 | |
| 57 | ```bash |
| 58 | claude mcp add --transport http exa https://mcp.exa.ai/mcp |
| 59 | ``` |
| 60 | </details> |
| 61 | |
| 62 | <details> |
| 63 | <summary><b>Claude Desktop</b></summary> |
| 64 | |
| 65 | Exa is available as a native Claude Connector — no config files or terminal commands needed. |
| 66 | |
| 67 | 1. Open Claude Desktop **Settings** (or **Customize**) and go to **Connectors** |
| 68 | 2. Search for **Exa** in the directory |
| 69 | 3. Click **+** to add it |
| 70 | |
| 71 | That's it! Claude will now have access to Exa's search tools. |
| 72 | |
| 73 | <details> |
| 74 | <summary>Alternative: manual config</summary> |
| 75 | |
| 76 | Add to your config file (`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS, `%APPDATA%\Claude\claude_desktop_config.json` on Windows): |
| 77 | |
| 78 | ```json |
| 79 | { |
| 80 | "mcpServers": { |
| 81 | "exa": { |
| 82 | "command": "npx", |
| 83 | "args": ["-y", "mcp-remote", "https://mcp.exa.ai/mcp"] |
| 84 | } |
| 85 | } |
| 86 | } |
| 87 | ``` |
| 88 | </details> |
| 89 | </details> |
| 90 | |
| 91 | <details> |
| 92 | <summary><b>Codex</b></summary> |
| 93 | |
| 94 | ```bash |
| 95 | codex mcp add exa --url https://mcp.exa.ai/mcp |
| 96 | ``` |
| 97 | </details> |
| 98 | |
| 99 | <details> |
| 100 | <summary><b>OpenCode</b></summary> |
| 101 | |
| 102 | Add to your `opencode.json`: |
| 103 | |
| 104 | ```json |
| 105 | { |
| 106 | "mcp": { |
| 107 | "exa": { |
| 108 | "type": "remote", |
| 109 | "url": "https://mcp.exa.ai/mcp", |
| 110 | "enabled": true |
| 111 | } |
| 112 | } |
| 113 | } |
| 114 | ``` |
| 115 | </details> |
| 116 | |
| 117 | <details> |
| 118 | <summary><b>Antigravity</b></summary> |
| 119 | |
| 120 | Open the MCP Store panel (from the "..." dropdown in the side panel), then add a custom server with: |
| 121 | |
| 122 | ``` |
| 123 | https://mcp.exa.ai/mcp |
| 124 | ``` |
| 125 | </details> |
| 126 | |
| 127 | <details> |
| 128 | <summary><b>Windsurf</b></summary> |
| 129 | |
| 130 | Add to `~/.codeium/windsurf/mcp_config.json`: |
| 131 | |
| 132 | ```json |
| 133 | { |
| 134 | "mcpServers": { |
| 135 | "exa": { |
| 136 | "serverUrl": "https://mcp.exa.ai/mcp" |
| 137 | } |
| 138 | } |
| 139 | } |
| 140 | ``` |
| 141 | </details> |
| 142 | |
| 143 | <details> |
| 144 | <summary><b>Zed</b></summary> |
| 145 | |
| 146 | Add to your Zed settings: |
| 147 | |
| 148 | ```json |
| 149 | { |
| 150 | "context_servers": { |
| 151 | "exa": { |
| 152 | "url": "https://mcp.exa.ai/mcp" |
| 153 | } |
| 154 | } |
| 155 | } |
| 156 | ``` |
| 157 | </details> |
| 158 | |
| 159 | <details> |
| 160 | <summary><b>Gemini CLI</b></summary> |
| 161 | |
| 162 | Add to `~/.gemini/settings.json`: |
| 163 | |
| 164 | ```json |
| 165 | { |
| 166 | "mcpServers": { |
| 167 | "exa": { |
| 168 | "httpUrl": "https://mcp.exa.ai/mcp" |
| 169 | } |
| 170 | } |
| 171 | } |
| 172 | ``` |
| 173 | </details> |
| 174 | |
| 175 | <details> |
| 176 | <summary><b>v0 by Vercel</b></summary> |
| 177 | |
| 178 | In v0, select **Prompt Tools** > **Add MCP** and enter: |
| 179 | |
| 180 | ``` |
| 181 | https://mcp.exa.ai/mcp |
| 182 | ``` |
| 183 | </details> |
| 184 | |
| 185 | <details> |
| 186 | <summary><b>Warp</b></summary> |
| 187 | |
| 188 | Go to **Settings** > **MCP Servers** > **Add MCP Server** and add: |
| 189 | |
| 190 | ```json |
| 191 | { |
| 192 | "exa": { |
| 193 | "url": "https://mcp.exa.ai/mcp" |
| 194 | } |
| 195 | } |
| 196 | ``` |
| 197 | </details> |
| 198 | |
| 199 | <details> |
| 200 | <summary><b>Kiro</b></summary> |
| 201 | |
| 202 | Add to `~/.kiro/settings/mcp.json`: |
| 203 | |
| 204 | ```json |
| 205 | { |
| 206 | "mcpServers": { |
| 207 | "exa": { |
| 208 | "url": "https://mcp.exa.ai/mcp" |
| 209 | } |
| 210 | } |
| 211 | } |
| 212 | ``` |
| 213 | </details> |
| 214 | |
| 215 | <details> |
| 216 | <summary><b>Roo Code</b> |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
