Exa

Learn how to use Klavis to connect your AI application to Exa MCP Server

No-Code

Connect to enterprise-grade MCP servers instantly!

Get Started →

---

For Developer

Follow the instructions below to integrate Exa MCP server to your AI application using our API or SDK.

Prerequisites

• Create an API key

1. Create an Exa MCP Server

Use the following endpoint to create a new remote Exa MCP server instance:

Request

Python

from klavis import Klavis
from klavis.types import McpServerName

klavis_client = Klavis(api_key="<YOUR_API_KEY>")

# Create an Exa MCP server instance
exa_server = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.EXA,
    user_id="<YOUR_USER_ID>",
    platform_name="<YOUR_PLATFORM_NAME>",
)

Response

Response

{
  "serverUrl": "https://exa-mcp-server.klavis.ai/mcp/?instance_id=<instance-id>",
  "instanceId": "<instance-id>"
}

serverUrl specifies the endpoint of the Exa MCP server, which allows you to perform AI-powered semantic search, content retrieval, similarity discovery, and comprehensive research through the Exa Search API.

instanceId is used for authentication and identification of your server instance.

2. Configure Exa API Key

To use the Exa MCP Server, you need to configure it with your Exa API key. You can get your API key from the Exa AI website.

Setting up Exa API Key

cURL

curl --request POST \
  --url https://api.klavis.ai/mcp-server/instance/set-auth \
  --header 'Authorization: Bearer <YOUR_KLAVIS_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
  "instanceId": "<YOUR_INSTANCE_ID>",
  "authData": {
    "token": "<YOUR_EXA_API_KEY>"
  }
}'

Response

Response

{
  "success": true,
  "message": "<string>"
}

Explore MCP Server Tools

Tools Information

Tool Name	Description
exa_search	Perform AI-powered semantic search across the web using neural or keyword search with advanced filtering options including domains, dates, and content patterns
exa_get_contents	Retrieve clean, parsed HTML content from web pages using their Exa result IDs with optional highlighting and summarization
exa_find_similar	Discover web pages that are semantically similar to a given URL based on content meaning and context
exa_answer	Get direct, focused answers to specific questions by searching and analyzing web sources with citations
exa_research	Conduct comprehensive, multi-source research on topics with structured analysis and detailed citations

For more details about tool input schema, use the list_tool API.