Prerequisites
- A Sarj.ai account
- An API key — see Step 1 below
- Python:
pip install sarj-platform-sdk(recommended over rawrequests)
If you’re using the MCP Server with an OAuth-capable client
instead of the REST API, skip Step 1. The client receives an API key through
Sarj sign-in on first connect. Other MCP clients need a dashboard API key.
1
Get your API key
- Sign in at platform.sarj.ai
- Click Create API key and choose an expiration
- Select
calls:writeto place calls andcalls:readto retrieve results - Copy the key and store it securely
2
Verify your setup
Confirm the API is reachable with a health check. This endpoint is public, so a successful response does not validate your API key.Expected result:
data.status is "ok".3
Create your first call
Trigger an outbound voice call. Requires your API key and a scenario ID.Run the TypeScript example on Node.js 22 or newer, in a server or trusted local script. Keep your API key out of browser code.A successful request returns
202 Accepted. Save data.id; see the response schema.4
Track the call
Fetch the returned ID with GET /calls/, or use webhooks for push delivery.Reports are generated asynchronously for
completed and max_duration_reached calls. Other terminal states never receive a report; rare generation failures can leave an eligible call without one too. Bound your polling and handle a missing report. Prefer permanent_recording_url; during its rollout, fall back to recording_url when the permanent field is null.See the Python SDK guide for an inspection example and future-call scheduling.
