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

# Cadencercs Cadence API

The Cadence API registers RCS brands and agents, submits them for Google and carrier review, and runs conversations that send messages to opted-in numbers. It tracks consent, delivery evidence, per-carrier launch and verification state, and delivery webhooks. Sandbox keys simulate delivery so nothing reaches a phone while you build, and three operations are irreversible unless re-sent with a confirmation flag.

## For AI agents

Register RCS brands and agents, run conversations and send messages, check consent and delivery, and track carrier launch and verification state.

## Scope

Does not handle email delivery, voice calls, or payment processing. Use for RCS brand and agent registration, messaging, and delivery only.

## Capabilities

- Register brands and agents and submit them for Google and carrier review
- Open conversations and send RCS messages to opted-in numbers
- Check whether a brand may message a given number before sending
- Register delivery webhooks and inspect recent delivery attempts
- Poll per-carrier launch and verification state for an agent
- Simulate inbound replies with a sandbox key without touching Google

## Use cases

### Agent-driven RCS onboarding

An AI agent can create a brand, add an agent to it, run the readiness check, and submit it for carrier review, then poll verification and launch state per carrier until it is live. Sandbox keys let the whole flow run without touching Google.

Example prompt: Create a brand, add an agent, run the readiness check, and submit the brand for carrier review

### Consent-checked messaging

A messaging agent can confirm a brand may message a number, open a conversation, send the message, and read the delivery evidence, so it never sends to a number that has not opted in. Re-consent events can be recorded for someone who opted back in.

Example prompt: Check that the brand may message +15551234567, open a conversation, and send a text message

### Delivery webhook monitoring

An operations agent can register a delivery webhook, send a signed test event, and inspect recent delivery attempts to confirm inbound activity is routed correctly. Cadence distinguishes delivery webhooks from Google inbound routing so the two are not confused.

Example prompt: Register a delivery webhook, send a signed test event, and list its recent delivery attempts

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/v1/brands` | Create a brand |
| POST | `/v1/brands/{id}/submit` | Submit a brand for carrier review |
| POST | `/v1/conversations` | Open a conversation and send the first message |
| GET | `/v1/brands/{id}/optins/{e164}` | Check if a brand may message a number |
| POST | `/v1/webhooks` | Register a delivery webhook |
| POST | `/v1/conversations/{id}/simulate-inbound` | Simulate an inbound reply |

## Key resources

- **Brands** — Create brands, run readiness checks, and submit them for carrier review
- **Agents** — Create RCS agents, request verification, and poll launch readiness
- **Conversations** — Open conversations, send messages, and read delivery evidence
- **Consent** — Check whether a brand may message a number and record re-consent
- **Delivery webhooks** — Register webhooks, send test events, and inspect delivery attempts

## 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:** 64 / 100
- **Maturity:** AI-Aware
- **Dimensions:**
  - Foundational Compliance: 74 / 100
  - Developer Experience & Jentic Compatibility: 70 / 100
  - AI-Readiness & Agent Experience: 48 / 100
  - Agent Usability: 88 / 100
  - Security: 60 / 100
  - AI Discoverability: 67 / 100
- **View full report:** https://jentic.com/apis/cadencercs.com/cadencercs/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 Cadence by hand means handling its bearer-token auth, choosing between its production and secondary hosts, and respecting the confirmation flag three irreversible operations require. Through Jentic you install once, import Cadence from the API Directory, store the token once, and your agent calls it.
- **Permission scoping:** You choose which Cadence operations the agent may call, such as conversations and consent checks, so irreversible operations like deleting a brand are not included unless you add them.
- **Credential handling:** Your Cadence token 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 'send an RCS message to a number', and Jentic returns the matching Cadence operation with its input schema so the agent calls the right endpoint without browsing the docs.

## Related APIs

- **Sinch** — Sinch offers RCS and SMS across carriers; Cadence focuses on Google RCS brand and agent onboarding.
- **Telnyx** — Telnyx is a programmable messaging and voice platform; Cadence specialises in RCS Business Messaging.
- **Plivo** — Plivo sends SMS and voice globally; Cadence handles the RCS brand-verification flow.

## FAQ

### What authentication does the Cadence API use?

The Cadence API authenticates with a bearer token in the Authorization header, per its OpenAPI spec. Signup and a few onboarding endpoints need no credential, and sandbox keys let you build without reaching a real phone.

### Is there a Cadence MCP server?

You do not need an MCP server to give your agent Cadence. Jentic connects it directly from the API Directory: import it, store your token once, and your agent calls the brand, conversation, and webhook operations without loading another server's tool definitions into its context.

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

Yes. Write a rule that allows only conversation and consent-check operations, so the agent can message opted-in numbers but cannot delete a brand or an agent until you add those irreversible operations, and every call it makes is logged.

### Can I check whether a brand may message a number with the Cadence API?

Yes. The brand opt-in endpoint answers whether a specific brand may message a specific E.164 number, so an agent can confirm consent before opening a conversation.

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

The OpenAPI spec does not publish a numeric rate limit. Carrier and Google review timelines govern how quickly a brand goes live, and the observed-verification-times endpoint reports current estimates.

### How do I send an RCS message with the Cadence API through Jentic?

Search Jentic for 'send an RCS message to a number', and it returns the Cadence conversation operation with its input schema. Confirm consent, open a conversation, and send the message, using a sandbox key while you build. To run it on your own infrastructure, install Jentic One from its GitHub repo.