MCP Server
RTGS.global provides an MCP (Model Context Protocol) server that lets AI-powered developer tools access the RTGS.global API documentation, integration guides, and recipes directly from your editor.
Server URL: https://mcp.rtgs.global/mcp
Setup
Select your AI tool to get started:
- Claude Code
- Claude Desktop
- Cursor
- VS Code
Run this command in your terminal:
claude mcp add --transport http rtgs-docs https://mcp.rtgs.global/mcp
This adds the server to your user-level config so it's available in every project. Alternatively, add it to your project's .mcp.json to share it with your team:
{
"mcpServers": {
"rtgs-docs": {
"type": "http",
"url": "https://mcp.rtgs.global/mcp"
}
}
}
Run /mcp to confirm the server is connected.
Add the server to your claude_desktop_config.json:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"rtgs-docs": {
"type": "streamable-http",
"url": "https://mcp.rtgs.global/mcp"
}
}
}
Restart Claude Desktop to apply the change.
Add the server to ~/.cursor/mcp.json (global) or .cursor/mcp.json in your project root:
{
"mcpServers": {
"rtgs-docs": {
"url": "https://mcp.rtgs.global/mcp"
}
}
}
Restart Cursor and check Settings → MCP to confirm the server appears.
Add the server to .vscode/mcp.json in your project root:
{
"servers": {
"rtgs-docs": {
"type": "http",
"url": "https://mcp.rtgs.global/mcp"
}
}
}
Available Tools
| Tool | Description |
|---|---|
search_docs | Full-text search across guides, integration recipes, and API endpoints |
get_endpoint | Fetch full details for a specific Participant Gateway API endpoint by path and method |
get_recipe | Retrieve a step-by-step integration recipe for a specific payment flow |
Test Your Setup
Once connected, try asking your AI assistant:
- "What are the steps to initiate a Link and Settle payment?"
- "Show me the request body for the Payaway endpoint"
- "How do I verify a webhook signature?"
- "What events does the FX Quotes flow produce?"
The assistant will call the appropriate tools and synthesise an answer from the live documentation.