​
No-Code

Connect to enterprise-grade MCP servers instantly!Klavis MCP Servers - No Code CreationGet Started →

​
For Developer

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

​
Prerequisites

​
1. Create a Brave Search MCP Server

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

​
Request

from klavis import Klavis
from klavis.types import McpServerName

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

# Create a Brave Search MCP server instance
brave_search_server = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.BRAVE_SEARCH,
    user_id="<YOUR_USER_ID>"
)

​
Response

{
  "serverUrl": "https://brave-search-mcp-server.klavis.ai/sse?instance_id=<instance-id>",
  "instanceId": "<instance-id>"
}
serverUrl specifies the endpoint of the Brave Search MCP server, which allows you to perform web, image, news, and video searches through the Brave Search API.
instanceId is used for authentication and identification of your server instance.

​
2. Configure Brave Search API Key

To use the Brave Search MCP Server, you need to configure it with your Brave Search API key.

​
Setting up Brave Search API Key

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_BRAVE_SEARCH_API_KEY>"
  }
}'

​
Response

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

​
Explore MCP Server Tools

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