Skip to main content
If you already run an AI coding agent — Claude Code, Cursor, Codex, or similar — it can stand up your Zelto organization for you over the MCP server: connect a call provider, create a monitor, wait for the first finding, and set up delivery. This page is both the human walkthrough and the script the agent follows (it reads the same steps through the read_docs tool).

​
Before you start

The one thing the agent can’t do for you is bootstrap its own access:
  1. Mint an API key at Settings → Integrations → API Call Upload in the dashboard. It’s shown once — copy it.
  2. Connect the Zelto MCP server in your editor with that key — see MCP for the per-client config. Confirm with the health tool (it returns your org id).
Everything below runs against the onboarding tools on that connection.

​
The flow

1

Check where you are

The agent calls get_onboarding_status first. It returns the ordered setup steps — connect a provider, create a monitor, receive a first finding, set up delivery — each with a done flag, plus nextIncomplete. Re-running onboarding is safe: the agent resumes from the first incomplete step.
2

Connect a call provider

The agent calls list_integrations to see what’s already connected, asks which stack you run, then connect_integration with the provider (vapi, retell, speechify, telnyx, or elevenlabs) and your provider apiKey. The key is validated against the provider and stored encrypted.For Vapi, Retell, and Speechify, the response includes a webhook.webhookUrl you paste into that provider’s dashboard — the one step only you can do. ElevenLabs and Telnyx sync automatically, no webhook needed.
3

Get calls flowing

Calls arrive once the webhook is pasted (or the hourly sync runs for the pull-based providers). The agent polls list_conversations until the first call lands. On a first call, Zelto creates the agent automatically. Already have history in a connected Retell account? The agent can import it with retell_import_agent and retell_import_conversations instead of waiting.
4

Create a monitor

A monitor is an AI judge that runs against every call and flags the ones that match a rubric. The agent offers the ready-made catalog from list_starter_monitors (refusals, task failure, user frustration, and more), then calls create_monitor — either with a starterKey, or with a name and a plain-language yes/no instruction of your own. It confirms with list_monitors.
5

Wait for the first finding

As calls flow through the monitor, Zelto surfaces findings — durable, org-level issues grouped from the calls that matched. The agent polls list_findings (or watches the firstFinding flag on get_onboarding_status) until the first one appears.
6

Route findings to your team

Finally the agent calls set_findings_delivery with the channels you want — email and/or slack. Slack additionally needs the Slack app connected via OAuth under Settings → Integrations, which the agent will flag for you to do.

​
Use your coding agent

Paste the prompt below into the coding agent in your editor. It loads the zelto-onboarding skill if your client supports Anthropic Agent Skills, or falls back to reading this page through read_docs — either way it follows the flow above and pauses for the steps only you can do.
Paste into your coding agent

​
Install the skill

Three ways to give your agent the skill, lowest-friction first:
  1. Zero-install (works with any MCP client). Every connected editor already has the read_docs tool — the paste-prompt above tells the agent to read_docs('onboarding-with-an-agent') and follow it. This always reflects the live version of this page. Recommended.
  2. Copy the skill folder (Claude Code and other Skills-capable clients). Drop the zelto-onboarding skill folder into your agent’s skills directory (for Claude Code, .claude/skills/). The skill’s SKILL.md plus its references/ files drive the same flow with progressive detail.
  3. Reference it inline. Point the agent at this page’s URL in your own prompt; it will read_docs the current version on demand.