3.1 Installation#
3.
Set up environment variables:Copy .env.example to .env
Fill in your credentials:USER_ID=your_user_id
API_KEY_TOKEN=your_api_key_token
PORT=8000
Note: You can either set USER_ID and API_KEY_TOKEN in the .env file, or pass them from your AI agent via headers:Authorization: Bearer <api_key_token>
The server will start on the port specified in your .env file (default: 8000).3.2 Authorization#
You can authenticate using:
• a Basic Auth
• a User Token (generated via Basic Auth),
• an API Key Token, or
• a Public API Key.To use the MCP, you'll need a User Id and an API Key Token, if you haven't added them to .env file you must include them in the headers.Just paste your API key into the header as:| Header | Value |
| --- | --- | --- | --- |
| Authorization | Bearer API_KEY_TOKEN |
| User-Id | USER_ID |Once that’s set, you’re ready to make authenticated requests to any Clara tool.The MCP server exposes the following Clara API endpoints as tools:agent.supported_attachments
3.4 Rate Limits#
API rate limits apply per API key. Clara allows up to 10 requests per second.
If you go over this limit, or exceed your plan’s usage limits, the API will return an HTTP 429 - Too Many Requests response.Keeping your usage within the limit ensures smooth and reliable performance for everyone.Modified at 2025-11-29 03:49:52