canonical: https://jentic.com/apis/canarics.com/canarics

# Canarics API

The Canarics API lets an AI assistant check a team's Canarics account for AI voice agents: minutes used versus plan, the voice agents themselves, call history, conversations, and per-day call statistics. It can schedule a voice-agent callback, draft outbound calling campaigns, and define custom mid-call tools, each gated by a scope on the key. A no-auth signup flow can set up a new team and hand back a one-time key.

## For AI agents

Read minutes used, list AI voice agents, read call history and statistics, schedule callbacks, and draft outbound calling campaigns for a team.

## Scope

Does not handle SMS, email, or payment processing beyond returning a hosted checkout link. Use for AI voice-agent account data, call history, and callbacks only.

## Capabilities

- Read minutes used versus plan for the current billing cycle
- List the team's AI voice agents and their dashboard links
- Read call logs, conversations, and per-day call statistics
- Look up the cross-call history for a single phone number
- Schedule an AI voice-agent callback to a phone number
- Draft outbound calling campaigns and define custom mid-call tools

## Use cases

### Agent-checked account status

An AI assistant can check a Canarics team's minute usage against its plan, list the voice agents, and read recent call statistics in one session, so the person asking gets an account summary without opening the dashboard. Reads are gated by the key's scope.

Example prompt: Read the minutes used versus plan this cycle and list the team's AI voice agents

### Scheduled voice callbacks

A support agent can look up the cross-call history for a phone number, then schedule a voice-agent callback to that number with a reason, so a follow-up call is placed without a human dialling. Scheduling a callback requires the callbacks scope on the key.

Example prompt: Look up the call history for +15551234567, then schedule a voice-agent callback with a reason

### Outbound campaign drafting

A growth agent can draft an outbound calling campaign from a brief and define a custom mid-call tool the voice agent can use, then dry-run the tool through the live-call executor before anything goes out. Drafting a campaign never places calls on its own.

Example prompt: Draft an outbound calling campaign from a brief and create a custom mid-call tool, then dry-run the tool

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/api/v1/usage` | Minutes used versus plan this cycle |
| GET | `/api/v1/agents` | List the team's AI voice agents |
| GET | `/api/v1/calls` | Read call log summaries |
| GET | `/api/v1/contacts/{number}` | Cross-call history for one number |
| POST | `/api/v1/callbacks` | Schedule a voice-agent callback |
| POST | `/api/v1/campaigns` | Draft an outbound calling campaign |

## Key resources

- **Usage** — Read minutes used versus plan for the billing cycle
- **Agents** — List the team's AI voice agents and their dashboard links
- **Calls** — Read call logs, conversations, per-day statistics, and per-number history
- **Callbacks** — Schedule an AI voice-agent callback to a number
- **Campaigns** — List and draft outbound calling campaigns
- **Tools** — List, create, and dry-run custom mid-call tools on voice agents

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 47 / 100
- **Maturity:** Foundational
- **Dimensions:**
  - Foundational Compliance: 83 / 100
  - Developer Experience & Jentic Compatibility: 61 / 100
  - AI-Readiness & Agent Experience: 22 / 100
  - Agent Usability: 94 / 100
  - Security: 55 / 100
  - AI Discoverability: 73 / 100
- **View full report:** https://jentic.com/apis/canarics.com/canarics/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring Canarics by hand means handling two auth schemes, a bearer token or an x-api-key header, and the per-scope gating that governs callbacks, campaigns, and tools. Through Jentic you install once, import Canarics from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** You choose which Canarics operations the agent may call, such as usage and call-log reads, so operations that schedule a callback or draft a campaign are not included unless you add them.
- **Credential handling:** Your Canarics key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'check voice minutes used this cycle', and Jentic returns the matching Canarics operation with its input schema so the agent calls the right endpoint without browsing the docs.

## Related APIs

- **Telnyx** — Telnyx is a programmable voice platform; Canarics manages AI voice agents and their call data.
- **Plivo** — Plivo offers programmable voice and SMS; Canarics focuses on AI voice-agent accounts and callbacks.
- **Sinch** — Sinch provides voice and messaging across carriers; Canarics centres on AI voice-agent operations.

## FAQ

### What authentication does the Canarics API use?

The Canarics API authenticates with a bearer token or an x-api-key header, per its OpenAPI spec. The discovery and signup endpoints need no credential, and individual operations are further gated by scopes on the key.

### Is there a Canarics MCP server?

Canarics runs a remote MCP server, exposed as a streamable HTTP endpoint. You can also connect Canarics directly through Jentic: your agent gets the account, call, and campaign operations from the spec without loading another server's tool definitions into its context, your key is injected at call time by your self-hosted instance, and your rules decide which operations the agent may call.

### Can I limit what my agent is allowed to do with the Canarics API?

Yes. Write a rule that allows only the usage and call-log read operations, so the agent can report account status but cannot schedule a callback or draft a campaign until you add those operations, and every call it makes is logged.

### Can I schedule a voice-agent callback with the Canarics API?

Yes. The callbacks endpoint schedules an AI voice-agent callback to a number with a reason, provided the key carries the callbacks scope, so an agent can arrange a follow-up call.

### What are the rate limits for the Canarics API?

The OpenAPI spec does not publish a numeric rate limit. Daily call statistics are capped at a 90-day window, and voice usage is bounded by the minutes your plan includes, which the usage endpoint reports.

### How do I check voice minutes with the Canarics API through Jentic?

Search Jentic for 'check voice minutes used this cycle', and it returns the Canarics usage operation with its input schema. Read minutes used versus plan, then list the voice agents or call history as needed. To run it on your own infrastructure, install Jentic One from its GitHub repo.