​
No-Code

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

​
For Developer

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

​
Prerequisites

​
1. Create an OpenRouter MCP Server

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

​
Request

from klavis import Klavis
from klavis.types import McpServerName

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

# Create an OpenRouter MCP server instance
openrouter_server = klavis_client.mcp_server.create_server_instance(
    server_name=McpServerName.OPENROUTER,
    user_id="<YOUR_USER_ID>",
    platform_name="<YOUR_PLATFORM_NAME>",
)

​
Response

{
  "serverUrl": "https://openrouter-mcp-server.klavis.ai/sse?instance_id=<instance-id>",
  "instanceId": "<instance-id>"
}
serverUrl specifies the endpoint of the OpenRouter MCP server. You can connect with your MCP client using SSE or the StreamableHTTP endpoint.
instanceId is used for authentication and identification of your server instance.

​
2. Configure OpenRouter API Key

To use the OpenRouter MCP Server, configure it with your OpenRouter API key. The server expects this key in the x-auth-token header at runtime. You can store it using the Set Auth Token API:

​
Setting up OpenRouter 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_OPENROUTER_API_KEY>"
}'

​
Response

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

​
Explore MCP Server Tools

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