canonical: https://jentic.com/apis/swagger.io/swagger

# Swagger Generator

This is an online swagger codegen server. You can find out more at https://github.com/swagger-api/swagger-codegen or on [irc.freenode.net, #swagger](http://swagger.io/irc/). The API exposes 7 endpoints.

## For AI agents

Programmatically gets languages supported by the client generator, generates a client library. Covers 7 operations.

## Scope

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

## Capabilities

- Gets languages supported by the client generator
- Generates a client library
- Returns options for a client library
- Downloads a pre-generated file
- Monitor Swagger Generator operational status and events

## Use cases

### Developer Tools Operations

Use the Swagger Generator to perform developer tools operations programmatically. The API provides 7 endpoints covering core functionality including gets languages supported by the client generator, generates a client library, returns options for a client library.

Example prompt: Call GET `/gen/clients` to gets languages supported by the client generator

### Automated gen Management

Automate gen operations by combining multiple Swagger Generator endpoints. Agents can generates a client library and then returns options for a client library in a single workflow.

Example prompt: Call POST `/gen/clients/{language}` to generates a client library, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call Swagger Generator 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 'gets languages supported by the client generator', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/gen/clients` | Gets languages supported by the client generator |
| POST | `/gen/clients/{language}` | Generates a client library |
| GET | `/gen/clients/{language}` | Returns options for a client library |
| GET | `/gen/download/{fileId}` | Downloads a pre-generated file |
| GET | `/gen/servers` | Gets languages supported by the server generator |
| POST | `/gen/servers/{framework}` | Generates a server library |
| GET | `/gen/servers/{framework}` | Returns options for a server framework |

## Key resources

- **gen** — Operations related to gen
- **clients** — Operations related to clients
- **servers** — Operations related to servers

## Why Jentic

- **Setup:** Wiring the Swagger Generator by hand means posting spec payloads to generator.swagger.io and polling for the generated file yourself, even though it takes no auth. Through Jentic you install once, import the Swagger Generator from the API Directory, and your agent calls it with no credential to manage.
- **Permission scoping:** The Swagger Generator puts the language, framework, and file id in the URL path (`/gen/clients/{language}`, `/gen/servers/{framework}`, `/gen/download/{fileId}`), so a rule can pin your agent to one language or framework. You choose the operations it may call, so generation is only included alongside the listing and download operations you allow.
- **Credential handling:** The Swagger Generator takes no credential, so there is nothing to store, and your own Jentic One instance still injects any configured settings at execution time. No secret enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'list supported client languages' or 'generate a client for a language', and Jentic returns the matching Swagger Generator 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 Swagger Generator use?

The Swagger Generator 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 gets languages supported by the client generator with the Swagger Generator?

Yes. Use the GET `/gen/clients` endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the Swagger Generator?

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 gets languages supported by the client generator through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'gets languages supported by the client generator'. Jentic returns the matching Swagger Generator operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the Swagger Generator have?

The Swagger Generator exposes 7 endpoints covering gen, clients, servers operations.

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

Yes. Because Jentic One is self-hosted, you set the rules that decide which Swagger Generator operations your agent may call and which values it may pass. You can allow only the listing operations (GET `/gen/clients`, GET `/gen/servers`) while blocking POST `/gen/clients/{language}` and POST `/gen/servers/{framework}`, so the agent can inspect supported languages without generating code. Since the language, framework, and file id all travel in the URL path, a rule can also pin the agent to a single language or framework and restrict downloads to GET `/gen/download/{fileId}.`