Vignetim OpenAI MCP

Conecte la API de Socios (Partner API) de Vignetim a Cursor, Windsurf, Continue, OpenAI Agents SDK y cualquier plataforma que soporte el Protocolo de Contexto de Modelo (Model Context Protocol).

Configuración rápida

Cursor

Abra Cursor Settings → MCP → Add new MCP server:

{
	"mcpServers": {
		"vignetim": {
			"url": "https://vignetim.com/api/mcp",
			"headers": {
				"X-API-Key": "YOUR_API_KEY",
				"X-API-Secret": "YOUR_API_SECRET"
			}
		}
	}
}

Windsurf

Agregue a su configuración MCP de Windsurf:

{
	"mcpServers": {
		"vignetim": {
			"serverUrl": "https://vignetim.com/api/mcp",
			"headers": {
				"X-API-Key": "YOUR_API_KEY",
				"X-API-Secret": "YOUR_API_SECRET"
			}
		}
	}
}

Continue (VS Code)

Agregue a .continue/config.json:

{
	"mcpServers": [
		{
			"name": "vignetim",
			"url": "https://vignetim.com/api/mcp",
			"headers": {
				"X-API-Key": "YOUR_API_KEY",
				"X-API-Secret": "YOUR_API_SECRET"
			}
		}
	]
}

OpenAI Agents SDK (Python)

from openai_agents import Agent, MCPServerStreamableHttp

async with MCPServerStreamableHttp(
    url="https://vignetim.com/api/mcp",
    name="vignetim",
    headers={
        "X-API-Key": "YOUR_API_KEY",
        "X-API-Secret": "YOUR_API_SECRET",
    },
) as mcp:
    agent = Agent(
        name="Vignetim Partner",
        instructions="You manage Vignetim API integration. Browse products, create orders, and manage webhooks.",
        mcp_servers=[mcp],
    )
    result = await agent.run("List all Hungarian vignettes for cars")

OpenAI Agents SDK (Node.js)

import { Agent, MCPServerStreamableHttp } from '@openai/agents';

const mcp = new MCPServerStreamableHttp({
	url: 'https://vignetim.com/api/mcp',
	name: 'vignetim',
	headers: {
		'X-API-Key': 'YOUR_API_KEY',
		'X-API-Secret': 'YOUR_API_SECRET',
	},
});

await mcp.connect();

const agent = new Agent({
	name: 'Vignetim Partner',
	instructions: 'You manage Vignetim API integration.',
	mcpServers: [mcp],
});

const result = await agent.run('Show me my recent orders');

Herramientas disponibles (19 en total)

Productos (6 herramientas)

Herramienta	Método	Endpoint de la API
`list_tickets`	GET	`/products/tickets`
`get_ticket`	GET	`/products/tickets/:id`
`list_esim_packages`	GET	`/products/esim`
`list_insurance_products`	GET	`/products/insurance`
`get_insurance_product`	GET	`/products/insurance/:slug`
`list_vehicle_categories`	GET	`/products/vehicle-categories`

Pedidos (4 herramientas)

Herramienta	Método	Endpoint de la API
`create_order`	POST	`/orders`
`list_orders`	GET	`/orders`
`get_order`	GET	`/orders/:id`
`get_order_status`	GET	`/orders/:id/status`

Webhooks (5 herramientas)

Herramienta	Método	Endpoint de la API
`create_webhook`	POST	`/webhooks`
`list_webhooks`	GET	`/webhooks`
`update_webhook`	PUT	`/webhooks/:id`
`delete_webhook`	DELETE	`/webhooks/:id`
`test_webhook`	POST	`/webhooks/:id/test`

Documentación (4 herramientas -- sin autenticación requerida)

Herramienta	Descripción
`list_docs`	Listar todas las secciones de documentación de la API
`get_doc`	Obtener el contenido completo de una sección por slug
`search_docs`	Buscar en toda la documentación
`get_openapi_spec`	Obtener la URL de la especificación OpenAPI 3.0

Construir un agente personalizado

from openai_agents import Agent, MCPServerStreamableHttp, Runner

SYSTEM_PROMPT = """You are a Vignetim Partner API assistant.
You help manage e-vignette, eSIM, and insurance orders.

Available actions:
- Browse products (vignettes, eSIM packages, insurance)
- Create and track orders
- Set up and manage webhook notifications
- Search API documentation for integration help

Always confirm before creating orders or modifying webhooks.
Use sandbox mode for testing."""

async def main():
    async with MCPServerStreamableHttp(
        url="https://vignetim.com/api/mcp",
        name="vignetim",
        headers={
            "X-API-Key": "YOUR_KEY",
            "X-API-Secret": "YOUR_SECRET",
            "X-Environment": "sandbox",
        },
    ) as mcp:
        agent = Agent(
            name="Vignetim Assistant",
            instructions=SYSTEM_PROMPT,
            mcp_servers=[mcp],
        )
        result = await Runner.run(
            agent,
            "Set up webhooks for order.completed and order.failed events "
            "at https://myapp.com/api/webhooks/vignetim, then send a test event."
        )
        print(result.final_output)

Modo sandbox

Agregue X-Environment: sandbox a sus encabezados para usar la API de sandbox con pagos simulados:

{
	"headers": {
		"X-API-Key": "YOUR_SANDBOX_KEY",
		"X-API-Secret": "YOUR_SANDBOX_SECRET",
		"X-Environment": "sandbox"
	}
}

Alternativa: Acceso HTTP directo

Si su plataforma no soporta MCP:

Recurso	URL
Especificación OpenAPI	`https://vignetim.com/api/partner-openapi`
LLMs.txt	`https://vignetim.com/llms.txt`
AI Plugin	`https://vignetim.com/.well-known/ai-plugin.json`
Documentación de la API	`https://vignetim.com/es/developers/api-reference`

Solución de problemas

"API credentials required"

Las herramientas de la API necesitan ambos encabezados X-API-Key y X-API-Secret. Las herramientas de documentación funcionan sin credenciales.

Problemas de conexión

Verifique que el endpoint sea accesible:

curl -X POST https://vignetim.com/api/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

Limitación de velocidad

El servidor MCP respeta los límites de velocidad de la API de Socios: 100 solicitudes/min general, 10 solicitudes/min para creación de pedidos. El sandbox tiene un multiplicador de 5x.