Exa MCP server
{
"mcpServers": {
"exa": {
"type": "http",
"url": "https://mcp.exa.ai/mcp"
}
}
}{
"mcpServers": {
"exa": {
"type": "http",
"url": "https://mcp.exa.ai/mcp"
}
}
}{
"mcpServers": {
"exa": {
"type": "http",
"url": "https://mcp.exa.ai/mcp"
}
}
}{
"servers": {
"exa": {
"type": "http",
"url": "https://mcp.exa.ai/mcp"
}
}
}{
"mcpServers": {
"exa": {
"type": "http",
"url": "https://mcp.exa.ai/mcp"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 3.4.1
What it does
Exa MCP Server connects AI agents to web search, content fetching, and multi-step research capabilities. It exposes tools for searching the web and fetching webpage content as markdown, useful for agents that need to gather and process information from the web.
- Search the web for current information on a topic and retrieve clean, ready-to-use content.
- Fetch and read the full content of one or more webpages as formatted markdown.
- Run multi-step research tasks using Exa Agents for enrichment, list-building, and structured data extraction.
Tools this server exposes
| Tool | Does |
|---|---|
| web_search_exa | Search the web for any topic and get clean, ready-to-use content. |
| web_fetch_exa | Read a webpage's full content as clean markdown from one or more URLs. |
| agent_run | Run an Exa Agent for multi-step research, list-building, enrichment, and structured output. |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.