​
Prerequisites

To get the most out of this guide, you’ll need to:

​
1. Create a Firecrawl Deep Research MCP Server

Use the following endpoint to create a new remote Firecrawl Deep Research MCP server instance:

​
Request

curl --request POST \
  --url https://api.klavis.ai/mcp-server/instance/create \
  --header 'Authorization: Bearer <YOUR_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
  "serverName": "Firecrawl Deep Research",
  "userId": "<YOUR_USER_ID>",
  "platformName": "<YOUR_PLATFORM_NAME>"
}'

​
Response

{
  "serverUrl": "https://firecrawl-deepresearch-mcp-server.klavis.ai/sse?instance_id=<instance-id>",
  "instanceId": "<instance-id>"
}
serverUrl specifies the endpoint of the Firecrawl Deep Research MCP server, which you can connect and use this MCP Server to perform comprehensive research on any topic.
instanceId is used for authentication and identification of your server instance.

​
2. Configure Firecrawl API Key

To use the Firecrawl Deep Research MCP Server, you need to configure it with your Firecrawl API key.

​
Setting up Firecrawl API Key

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

​
Response

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

​
Explore MCP Server Tools