Exa
About
Query Exa API to retrieve structured search results.
Details
- Repository
- exa-labs/exa-mcp-server
- Transport
- SSE
- License
- MIT
Explore
- Hosted MCP server – no local installation required
- Web search and web fetch tools (enabled by default)
- Advanced search with filters, domains, and date ranges
- Optional Exa Agent for multi-step research and structured output
- Supports many MCP clients (Cursor, VS Code, Claude, Zed, etc.)
- Ready-to-use Claude Skills for company research and code search
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
ExaCommand (node, npx, python, etc.)nodeArguments-
Argument 1
server.js
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Connect to Exa's hosted MCP server:
```
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.
web_search_advanced_exa
Advanced search with filters, domains, dates, highlights, summaries, and subpage crawling.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"exa": {
"env": {},
"args": [
"server.js"
],
"command": "node"
}
}
}Linux
{
"env": [],
"args": [
"server.js"
],
"command": "node"
}Macos
{
"env": [],
"args": [
"server.js"
],
"command": "node"
}Windows
{
"env": [],
"args": [
"/c",
"node",
"server.js"
],
"command": "cmd"
}Exa provides web search and code documentation search for AI workflows. Its connector gives assistants live retrieval context for finding relevant web pages, technical documentation, and source material when answers need grounded external information.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
