canonical: https://jentic.com/apis/replicate.so/replicate-so

# Replicate So Integration API

API for managing integrations and webhooks. The API exposes 7 endpoints.

## For AI agents

Programmatically get integration by channel id, generate API key for a channel. Covers 7 operations.

## Scope

Does not handle payments, communications, or crm - use for developer tools only.

## Capabilities

- Get integration by channel ID
- Generate API key for a channel
- Validate API key
- Toggle integration status
- Add webhook
- Remove webhook

## Use cases

### Developer Tools Operations

Use the Integration API to perform developer tools operations programmatically. The API provides 7 endpoints covering core functionality including get integration by channel id, generate API key for a channel, validate API key.

Example prompt: Call GET `/integration/{channelId}` to get integration by channel id

### Automated integrations Management

Automate integrations operations by combining multiple Integration API endpoints. Agents can generate API key for a channel and then validate API key in a single workflow.

Example prompt: Call POST `/integration/{channelId}/generate-api-key` to generate API key for a channel, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call Integration API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle none tokens manually.

Example prompt: Search Jentic for 'get integration by channel id', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/integration/{channelId}` | Get integration by channel ID |
| POST | `/integration/{channelId}/generate-api-key` | Generate API key for a channel |
| POST | `/integration/validate-api-key` | Validate API key |
| POST | `/integration/{channelId}/toggle` | Toggle integration status |
| POST | `/integration/webhook` | Add webhook |
| DELETE | `/integration/webhook` | Remove webhook |
| GET | `/integration/feedback` | Get feedbacks by API key |

## Key resources

- **integrations** — Integration management
- **webhooks** — Webhook management
- **feedback** — Feedback retrieval

## 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: 100 / 100
  - Developer Experience & Jentic Compatibility: 63 / 100
  - AI-Readiness & Agent Experience: 21 / 100
  - Agent Usability: 94 / 100
  - Security: 100 / 100
  - AI Discoverability: 63 / 100
- **View full report:** https://jentic.com/apis/replicate.so/replicate-so/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 this Integration API by hand means constructing each request against the api.replicate.so host and tracking channel ids across integration and webhook calls yourself. Through Jentic you install once, import the Integration API from the API Directory, and your agent calls it.
- **Permission scoping:** The Integration API puts the channel id in the URL path (`/integration/{channelId}/...`), so a rule can pin your agent to one channel: it can read and toggle that channel. You choose the operations it may call, so a destructive one like webhook deletion is not included unless you add it.
- **Credential handling:** Any credential this integration needs 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 'get an integration by channel id' or 'generate an API key for a channel', and Jentic returns the matching Integration API operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Github** — Alternative developer tools API
- **Gitlab** — Alternative developer tools API

## FAQ

### What authentication does the Integration API use?

The Integration API uses no authentication. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.

### Can I get integration by channel id with the Integration API?

Yes. Use the GET `/integration/{channelId}` endpoint. The API returns structured JSON responses that agents can parse and act on directly.

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

Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.

### How do I get integration by channel id through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'get integration by channel id'. Jentic returns the matching Integration API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the Integration API have?

The Integration API exposes 7 endpoints covering integrations, webhooks, feedback operations.

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

Yes. Because you run Jentic One yourself, your own rules decide which of the Integration API's operations the agent may call and which credentials it may use. Since the channel id sits in the URL path (`/integration/{channelId}/...`), you can pin the agent to a single channel and grant only read and toggle-status calls, leaving out anything you do not want it touching. A destructive operation such as removing a webhook via DELETE `/integration/webhook` is only available to the agent if you explicitly include it.