# Exa MCP server > Search the web and fetch pages as clean markdown through Exa's search API, with optional agent runs and advanced search. - Listing: https://mcp.tc/i/exa - Connect: use the server's own URL `https://mcp.exa.ai/mcp` (sign-in optional); clients connect to it directly. The listing link is a page, not an MCP endpoint. - Type: remote (Streamable HTTP) - Auth: optional (works without sign-in) - Category: [Search & Web Data](https://mcp.tc/c/search-web) - Vendor: Exa - Homepage: - Repository: - Package: npm `exa-mcp-server` ## About Connects an assistant to Exa's search index. It can run web searches that return clean, ready-to-use text, and fetch the full content of one or more URLs as markdown. Queries work best when they describe the ideal page, and category filters can search people or company profiles. Runs as a hosted streamable HTTP endpoint at https://mcp.exa.ai/mcp. It works anonymously with rate limits. For higher limits, sign in with OAuth (add ?login to the URL) or pass an Exa API key via the exaApiKey URL parameter, a Bearer header or an x-api-key header. Optional tools such as agent\_run and web\_search\_advanced\_exa are enabled with the tools URL parameter. ## What it can do - Search the web and get clean text from top results - Fetch full page content as markdown from known URLs - Batch several URLs in one fetch call - Search LinkedIn-style people and company profiles by category - Optionally enable advanced search with filters and domains - Optionally run Exa Agent for multi-step research (requires sign-in) ## Tools (2) - `web_search_exa`: Search the web and return clean, ready-to-use content from top results. (read-only) - `web_fetch_exa`: Read the full content of one or more webpages as clean markdown. (read-only) ## Example prompts - "Find a blog post comparing React and Vue performance" - "Search for recent news about solid-state battery startups" - "Read https://exa.ai/docs and summarize the get started guide" - "Find companies building AI note-taking tools" ## Install ### Claude Code 1. Run this in a terminal, in your project folder: ```bash claude mcp add --transport http exa https://mcp.exa.ai/mcp ``` 2. Start Claude Code and type `/mcp`. **exa** should show as connected. To sign in for more access, pick it and choose **Authenticate**. Add `--scope user` to make it available in every project, not just this one. ### Claude Desktop 1. Open **Settings → Connectors** and click **Add custom connector**. 2. Name it **Exa** and paste this URL: ```url https://mcp.exa.ai/mcp ``` 3. Click **Add**, then **Connect**. Signing in to Exa is optional. Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too. ### claude.ai 1. Open the connector form on claude.ai. This button fills in the name and URL for you: [Add to claude.ai]() (opens connector settings) 2. Check that the URL reads `https://mcp.exa.ai/mcp` and click **Add**. 3. Click **Connect**. Signing in to Exa is optional. Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**. ### ChatGPT 1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**. 2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server. 3. Paste `https://mcp.exa.ai/mcp` as the server URL and choose **No authentication**, or **OAuth** to sign in to Exa for more access. Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts. ### Cursor [Add to Cursor]() (opens Cursor) Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project): `mcp.json`: ```json { "mcpServers": { "exa": { "url": "https://mcp.exa.ai/mcp" } } } ``` ### VS Code [Install in VS Code]() (opens VS Code) Or from a terminal: ```bash code --add-mcp '{"name":"exa","type":"http","url":"https://mcp.exa.ai/mcp"}' ``` Or commit it to the repo in `.vscode/mcp.json`: `.vscode/mcp.json`: ```json { "servers": { "exa": { "type": "http", "url": "https://mcp.exa.ai/mcp" } } } ``` ### Devin Desktop 1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows): `mcp_config.json`: ```json { "mcpServers": { "exa": { "serverUrl": "https://mcp.exa.ai/mcp" } } } ``` 2. Refresh the MCP server list in Cascade. Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers. ### Codex ```bash codex mcp add exa --url https://mcp.exa.ai/mcp ``` Or edit `~/.codex/config.toml` directly: `config.toml`: ```toml [mcp_servers.exa] url = "https://mcp.exa.ai/mcp" ``` ### Gemini CLI ```bash gemini mcp add --transport http exa https://mcp.exa.ai/mcp ``` Then, inside Gemini CLI, run `/mcp auth exa` to sign in (optional). This adds it to the current project. Add `-s user` to use it everywhere. ### Any client Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file. ```json { "mcpServers": { "exa": { "type": "http", "url": "https://mcp.exa.ai/mcp" } } } ``` Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE. Client only starts local servers? Bridge it with `npx -y mcp-remote https://mcp.exa.ai/mcp`. ## Details - Server version: 3.2.1 - MCP protocol version: 2025-11-25 - Last checked: 2026-10-03 (reachable) - Listed: 2026-10-03 - Updated: 2026-10-03 --- Source: https://mcp.tc/i/exa (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report