Developer MCP

The Airwallex Developer Model Context Protocol (MCP) server enables coding agents to search Airwallex documentation and interact with the sandbox environment for testing and simulation.

Two remote endpoints are available:

• https://mcp-demo.airwallex.com/developer: Provides access to documentation and sandbox tools. Requires OAuth authentication.
• https://mcp-demo.airwallex.com/docs: Provides documentation-only access without authentication.

A local server (npx @airwallex/developer-mcp@latest) runs on your machine via Node.js and provides full tool access, including billing tools, without OAuth. Authenticate using your sandbox API credentials.

Remote endpoints work seamlessly with both desktop and web-based AI assistants. Note that we do not currently support Billing tools on our developer MCP server.

Before you begin

Before you connect your coding assistant to the Developer MCP server, ensure you have:

• A compatible AI coding assistant installed (Cursor, Claude Code, or other MCP-compatible tool).
• A sandbox account if you want to use the remote /developer endpoint or the local server.
• Sandbox API credentials (Client ID and API Key) if you want to use the local server.
• Node.js version 18.x or later installed and available on your PATH if you want to use the local server.

Connect your AI assistant

Cursor

You can use one-click installation links or manual configuration.

Developer
Docs
Local

Documentation and sandbox tools at /developer. Cursor initiates OAuth to authenticate with Airwallex.

Or manually add to your Cursor MCP settings:

JSON

1{
2  "mcpServers": {
3    "airwallex-dev": {
4      "type": "http",
5      "url": "https://mcp-demo.airwallex.com/developer"
6    }
7  }
8}

Documentation-only access at /docs, without authentication.

Or manually add to your Cursor MCP settings:

JSON

1{
2  "mcpServers": {
3    "airwallex-docs": {
4      "type": "http",
5      "url": "https://mcp-demo.airwallex.com/docs"
6    }
7  }
8}

Full tool access including billing tools, without OAuth.

Or manually add the following to your Cursor MCP settings and fill in your sandbox credentials:

JSON

1{
2  "mcpServers": {
3    "airwallex-dev": {
4      "command": "npx",
5      "args": ["-y", "@airwallex/developer-mcp@latest"],
6      "env": {
7        "AIRWALLEX_SANDBOX_CLIENT_ID": "",
8        "AIRWALLEX_SANDBOX_API_KEY": "",
9        "AIRWALLEX_SANDBOX_ACCOUNT_ID": ""
10      }
11    }
12  }
13}

Claude Code

1claude mcp add-json airwallex-dev '{ "type": "http", "url": "https://mcp-demo.airwallex.com/developer" }'

1claude mcp add-json airwallex-docs '{ "type": "http", "url": "https://mcp-demo.airwallex.com/docs" }'

1claude mcp add-json airwallex-dev '{ "type": "stdio", "command":"npx", "args": ["-y", "@airwallex/developer-mcp@latest"], "env": { "AIRWALLEX_SANDBOX_CLIENT_ID": "", "AIRWALLEX_SANDBOX_API_KEY": "", "AIRWALLEX_SANDBOX_ACCOUNT_ID": "" } }'

Claude.ai/Claude Desktop

Gemini CLI

1{
2  "mcpServers": {
3    "airwallex-dev": {
4      "type": "http",
5      "url": "https://mcp-demo.airwallex.com/developer"
6    }
7  }
8}

1{
2  "mcpServers": {
3    "airwallex-docs": {
4      "type": "http",
5      "url": "https://mcp-demo.airwallex.com/docs"
6    }
7  }
8}

1{
2  "mcpServers": {
3    "airwallex-dev": {
4      "command": "npx",
5      "args": ["-y", "@airwallex/developer-mcp@latest"],
6      "timeout": 30000,
7      "env": {
8        "AIRWALLEX_SANDBOX_CLIENT_ID": "",
9        "AIRWALLEX_SANDBOX_API_KEY": "",
10        "AIRWALLEX_SANDBOX_ACCOUNT_ID": ""
11      }
12    }
13  }
14}

OpenAI Codex

1[mcp_servers.airwallex-dev]
2type = "http"
3url = "https://mcp-demo.airwallex.com/developer"

1[mcp_servers.airwallex-docs]
2type = "http"
3url = "https://mcp-demo.airwallex.com/docs"

1[mcp_servers.airwallex-dev]
2command = "npx"
3args = ["-y", "@airwallex/developer-mcp@latest"]
4
5[mcp_servers.airwallex-dev.env]
6AIRWALLEX_SANDBOX_CLIENT_ID = ""
7AIRWALLEX_SANDBOX_API_KEY = ""
8AIRWALLEX_SANDBOX_ACCOUNT_ID = ""

Lovable

Lovable is a web-based coding agent that only supports remote MCP servers. MCP server support requires a paid plan.

V0

V0 by Vercel is a web-based AI coding agent that only supports remote MCP servers. MCP server support requires a paid plan.

1{
2  "mcpServers": {
3    "airwallex-docs": {
4      "type": "http",
5      "url": "https://mcp-demo.airwallex.com/docs"
6    }
7  }
8}

Repl.it

Repl.it is a web-based AI coding agent that only supports remote MCP servers.

Local server configuration

The local server is configured via environment variables. Add these to the env block in your MCP settings:

Best practices

Always mention "Airwallex" in your prompts

When asking your coding assistant about Airwallex products, APIs, or integrations, explicitly mention "Airwallex" in your prompt. This helps the model select the appropriate MCP server and tools.

Examples:

• Integrate Airwallex's Drop-in Element with this website.
• Using Airwallex, can you find me test card numbers for the 3D Secure (3DS) authentication failure case?
• I tried to make a payout with Airwallex and got this error: amount_below_transfer_method_limit. What does that mean?

Use plan mode

Enable plan mode for complex tasks. This allows you to review the agent's planned actions before execution, ensuring you understand and approve each step of the implementation.

If you're using Cursor, you can activate plan mode in either of the following ways:

• Select Plan from the agent mode dropdown in Cursor's composer.
• Mention it explicitly in your prompt (for example, "Using plan mode, help me integrate Airwallex Embedded Elements").

Be specific with your requirements

Provide detailed context about your use case, including the specific Airwallex product or feature you're working with, your preferred programming language and framework, the environment (sandbox or production), and any specific business requirements or constraints.

Leverage sandbox credentials

Configure your sandbox API credentials to unlock additional MCP tools for testing and simulation. With sandbox credentials, the agent can:

• Create test transactions and billing plans.
• Simulate transfer status updates.
• Generate payment links for testing.
• Interact with your sandbox account directly.

This enables end-to-end development and testing workflows without leaving your coding environment.

Example:

• Can you create a new billing plan on Airwallex called Startup for $29.99/month and create a hosted URL to subscribe to it?

Tools

The Developer MCP server provides different tools depending on which endpoint or deployment you use:

Documentation tools

Available on: /developer endpoint, /docs endpoint, and local server

Sandbox tools

Available on: /developer endpoint and local server

All data retrieved and actions performed with the tools below are in the authenticated sandbox account.

Core Resources

Transactional FX

Payouts

Payment Acceptance

Issuing

Billing tools

Available on: local server only

All data retrieved and actions performed with the tools below are in the authenticated sandbox account.

Benefits

• Faster information retrieval: Instead of searching documentation websites, you receive relevant information directly in your coding environment, with access to your codebase for context.
• Reduced hallucination: AI models often lack up-to-date knowledge of specific APIs and may generate incorrect code. By providing current documentation and examples through MCP tools, the Airwallex Developer MCP server can reduce inaccurate responses.
• Workflow automation: You can perform common tasks like creating test resources, simulating actions, and testing integrations using natural language prompts, eliminating context switching between tools.
• Improved experience: Contextual assistance delivered directly to coding assistants helps you find information faster and write better code, reducing integration time.

Limitations

• Model dependency: The quality of responses depends on the AI model your coding assistant uses. Different models produce varying results, and no model is perfect.
• Sandbox only: Direct API testing tools work exclusively in Sandbox environments. Production operations require proper integration through direct API calls.
• Hallucination reduction, not elimination: While providing current documentation reduces incorrect responses, AI models can still generate inaccurate code or responses. Generated code must always be reviewed, validated, and tested before use in production environments.

Feedback

For questions or feedback about the Developer MCP server, contact the Developer Experience team at [email protected].

See also

• API reference API: Explore the full Airwallex API documentation
• Sandbox environment overview: Learn about testing in the Sandbox Environment