Our Model Context Protocol (MCP) server enables AI-powered code editors like Cursor and Windsurf, plus general-purpose tools like Claude Desktop to interact with the PPRO API. This enables developers to interact with PPRO’s platform more efficiently, streamline payment integrations, and build new commerce solutions faster.

What is MCP?

Model Context Protocol (MCP) is an open standard that allows AI applications to securely access external data sources and tools. The PPRO API MCP server provides AI agents with:

Direct API access to functionality
Schema search capabilities
Code generation assistance for integrations

MCP server setup

PPRO hosts a remote MCP server at https://developerhub.ppro.com/mcp. Configure your AI development tools to connect to this server.

To make API calls directly from your MCP client, configure authentication headers.

Add to~/.cursor/mcp.json:

{
"mcpServers": {
"ppro-global-api": {
  "url": "https://developerhub.ppro.com/mcp",
  "headers": {
    "Authorization": "Bearer {YOUR_API_KEY}",
    "Merchant-Id": "{YOUR_MERCHANT_ID}"
      }
    }
  }
}

Tools


Payment charges	`create-charge`: Creates a payment charge using the `paymentMethod` MOCK that requires authentication.
Others	`execute-request`: Sends an API request based on a HAR (HTTP Archive) request object. `get-code-snippet`: Generates a code snippet in a specified language for making a request to an endpoint. `get-endpoint`: Returns detailed information about a specific API endpoint, including parameters, request/response schemas, descriptions, and other details. `get-request-body`: Returns the schema/format of the request body for an endpoint (useful for POST, PUT, PATCH). `get-response-schema`: Returns the schema/format of the response for an endpoint, showing the structure of the data returned. `get-server-variables`: Returns server variables for each server in an OpenAPI spec. `list-endpoints`: Lists all endpoints in an OpenAPI spec. `list-security-schemes`: Returns all authentication/authorization methods supported by the API. `list-specs`: Lists all available OpenAPI specs. `search-specs`: Searches all available OpenAPI specs, including paths, operations, and schemas, using case-insensitive pattern matching and returns results from any matching spec.

Payment charges

create-charge: Creates a payment charge using the paymentMethod MOCK that requires authentication.

Others

execute-request: Sends an API request based on a HAR (HTTP Archive) request object.

get-code-snippet: Generates a code snippet in a specified language for making a request to an endpoint.

get-endpoint: Returns detailed information about a specific API endpoint, including parameters, request/response schemas, descriptions, and other details.

get-request-body: Returns the schema/format of the request body for an endpoint (useful for POST, PUT, PATCH).

get-response-schema: Returns the schema/format of the response for an endpoint, showing the structure of the data returned.

get-server-variables: Returns server variables for each server in an OpenAPI spec.

list-endpoints: Lists all endpoints in an OpenAPI spec.

list-security-schemes: Returns all authentication/authorization methods supported by the API.

list-specs: Lists all available OpenAPI specs.

search-specs: Searches all available OpenAPI specs, including paths, operations, and schemas, using case-insensitive pattern matching and returns results from any matching spec.

Testing Your MCP Setup

Once configured, you can test your MCP server connection:

Open your AI editor (Cursor, Windsurf, etc.)
Start a new chat with the AI assistant
Ask about PPRO API - try questions like:
- "How do I [common use case]?"
- "Show me an example of [API functionality]"
- "Create a [integration type] using PPRO API"