canonical: https://jentic.com/apis/automessage.app/automessage

# Automessage App autoMessage REST API

The autoMessage API sends and receives iMessages over standard HTTPS, relaying each message through a customer's own macOS connector and Apple ID. It queues outbound messages, exposes conversations and individual messages by their guid, and keeps editable drafts that can be updated or cancelled before they send. A contacts collection and a status endpoint let an agent confirm who it can reach and whether the connector is online.

## For AI agents

Send and track iMessages from a connected Apple device: queue outbound messages, read conversations, edit drafts before they send, and update the contacts the connector can reach.

## Scope

Does not handle SMS gateways, email, or push notifications. Use for sending and tracking iMessages through your own connected Apple device only.

## Capabilities

- Queue an outbound iMessage to a contact and track its delivery status
- List conversations and retrieve individual messages by their guid
- Draft a message, update it before it sends, and cancel it while still queued
- Create and update the contacts the connector is allowed to message
- Check connector liveness and the health of the macOS bridge

## Use cases

### AI Agent iMessage Outreach

An AI agent reaches customers over iMessage without a developer wiring the connector by hand. Through Jentic the agent imports the autoMessage API, queues an outbound message to a contact, and reads back the delivery status the macOS connector reports, all while the Apple ID and key stay on the developer's own machine.

Example prompt: Queue an outbound iMessage to the contact +15551234567 saying 'Your order shipped', then poll the message by its guid until the delivery status is confirmed

### Delivery Tracking

Teams that message customers over iMessage need to know which messages actually landed. autoMessage returns each queued message with a guid and a status the connector updates as Apple reports back, so a workflow can list recent messages and flag any that failed to deliver.

Example prompt: List messages from the last day and return the guid of any whose delivery status is not confirmed

### Draft Review Before Send

Some outbound messages should be reviewed before they leave the device. autoMessage lets an agent create a draft, update its text, and cancel it while it is still queued, so a human or a second check can approve the wording before the connector sends it.

Example prompt: Create a draft to a contact, update its body after review, and cancel it if the reviewer rejects the wording

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/messages` | Queue an outbound iMessage |
| GET | `/messages` | List messages |
| GET | `/messages/{guid}` | Retrieve a single message |
| GET | `/conversations` | List conversations |
| POST | `/drafts` | Create a draft |
| PATCH | `/drafts/{id}` | Update a draft before it sends |
| GET | `/contacts` | List contacts |
| GET | `/status` | Report connector liveness |

## Key resources

- **Messages** — Queue outbound iMessages, list them, and retrieve a single message by its guid
- **Drafts** — Create, update, and cancel messages that have not yet been sent
- **Conversations** — List conversations the connected device can see
- **Contacts** — Create, read, and update the contacts the connector can message
- **Status** — Report connector liveness and macOS bridge health

## 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:** 48 / 100
- **Maturity:** Foundational
- **Dimensions:**
  - Foundational Compliance: 72 / 100
  - Developer Experience & Jentic Compatibility: 60 / 100
  - AI-Readiness & Agent Experience: 24 / 100
  - Agent Usability: 94 / 100
  - Security: 50 / 100
  - AI Discoverability: 70 / 100
- **View full report:** https://jentic.com/apis/automessage.app/automessage/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 autoMessage by hand means provisioning its API key, pairing a macOS connector to an Apple ID, and handling message status polling yourself. Through Jentic you install once, import autoMessage from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** A single account key reaches every autoMessage operation, so a rule bounds the agent to the operations it needs, such as queuing and reading messages. You choose which operations it may call, so destructive ones like contact deletion are not included unless you add them.
- **Credential handling:** Your autoMessage 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 'send an iMessage' or 'check delivery status', and Jentic returns the matching autoMessage operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Twilio Messaging** — Twilio sends SMS and MMS over carrier networks rather than iMessage from an Apple device.
- **MessageBird SMS** — MessageBird delivers SMS globally through telecom gateways instead of a local macOS connector.
- **SendGrid Mail** — SendGrid delivers transactional email alongside autoMessage's device-sent iMessages.

## FAQ

### Is there an autoMessage MCP server?

You don't need an MCP server to give your agent the autoMessage API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls it. Because operations are discovered on demand, you avoid loading another server's tool definitions into the agent's context.

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

Yes. Write a rule that allows only the message-send and draft operations, so the agent can queue and review iMessages but cannot delete contacts, and every call it makes is logged for you to review.

### What authentication does the autoMessage REST API use?

The autoMessage REST API authenticates with an API key sent in the `X-API-KEY` header, as declared in its OpenAPI spec. Through Jentic that key is stored encrypted by your own Jentic One instance and injected at call time, so it never reaches the agent's prompt or logs.

### Can I send an iMessage and confirm it was delivered with the autoMessage API?

Yes. Queue the message with a post to the messages collection, then poll the message by its guid to read the delivery status the connector reports back as Apple confirms it.

### How do I send an iMessage through Jentic?

Install Jentic One with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, then import the autoMessage API from the Jentic API Directory and store your key. Your agent searches for 'send an iMessage' and Jentic returns the queue-message operation with its input schema. To run it on your own infrastructure, install Jentic One from its GitHub repo.

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

The autoMessage OpenAPI spec does not define rate limits. Because every message is relayed through your own Apple device, throughput is bounded by that device rather than a published API quota, so plan high-volume sends accordingly.