GoCardless MCP Server
Enables AI assistants to interact with GoCardless payment data, providing tools to manage customers, payments, mandates, subscriptions, and payouts. Includes Xero integration support for automatic parsing of metadata.
README
GoCardless MCP Server
A Model Context Protocol (MCP) server for GoCardless API integration, enabling AI assistants to interact with GoCardless payment data.
Features
This MCP server provides tools to:
- Customers: List, get, and create customers
- Payments: List, get, and create payments
- Mandates: List and get mandates
- Subscriptions: List and get subscriptions (including combined details with customer/mandate)
- Payouts: List payouts
- Xero Integration: Automatic detection and parsing of Xero contact/invoice/payment IDs from metadata
Limitations
- Read-only recommended: While customer and payment creation are supported, read-only API tokens are recommended for most use cases
- No update operations: Existing records cannot be modified
- No cancellation: Subscriptions, mandates, and payments cannot be cancelled through this server
Installation
Using uvx (Recommended for Claude Code/Cursor)
No installation required - uvx will automatically fetch and run the package:
uvx --from git+https://github.com/jmceleney/gocardless-mcp.git gocardless-mcp
Configure in your MCP settings (see configuration examples below).
Using pipx
pipx install git+https://github.com/jmceleney/gocardless-mcp.git
Using pip
pip install git+https://github.com/jmceleney/gocardless-mcp.git
Local Development
# Clone the repository
git clone https://github.com/jmceleney/gocardless-mcp.git
cd gocardless-mcp
# Install in development mode
pip install -e .
Configuration
Environment Variables
You'll need to configure these environment variables:
GOCARDLESS_ACCESS_TOKEN(required): Your GoCardless API access tokenGOCARDLESS_ENVIRONMENT(optional): Eithersandboxorlive(defaults tosandbox)
Get a GoCardless Access Token:
- Sign up for a GoCardless sandbox account
- Navigate to Developers > API tokens
- Create a new access token
- Copy the token for use in configuration
Setup for Different AI Tools
Claude Desktop
Claude Desktop is the easiest way to get started with MCP servers.
Configuration file location:
- MacOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%/Claude/claude_desktop_config.json
Add this configuration:
{
"mcpServers": {
"gocardless": {
"command": "gocardless-mcp",
"env": {
"GOCARDLESS_ACCESS_TOKEN": "your_access_token_here",
"GOCARDLESS_ENVIRONMENT": "sandbox"
}
}
}
}
After configuration:
- Restart Claude Desktop
- Look for the 🔨 (hammer) icon in the bottom-right corner
- Click it to verify the GoCardless server is connected
- Start asking questions like "Show me my recent GoCardless customers"
Claude Code
Claude Code works best with uvx for automatic package management.
Method 1: Using uvx (Recommended)
claude mcp add gocardless \
--env GOCARDLESS_ACCESS_TOKEN=your_token_here \
--env GOCARDLESS_ENVIRONMENT=sandbox \
-- uvx --from git+https://github.com/jmceleney/gocardless-mcp.git gocardless-mcp
Method 2: Edit Configuration File Directly
Edit ~/.claude.json:
{
"mcpServers": {
"gocardless": {
"type": "stdio",
"command": "uvx",
"args": ["--from", "git+https://github.com/jmceleney/gocardless-mcp.git", "gocardless-mcp"],
"env": {
"GOCARDLESS_ACCESS_TOKEN": "your_access_token_here",
"GOCARDLESS_ENVIRONMENT": "sandbox"
}
}
}
}
After configuration:
- Restart Claude Code
- Verify with:
claude mcp list - The GoCardless server should appear in the list
Cursor IDE
Cursor works best with uvx for automatic package management.
Project-specific configuration (recommended):
Create .cursor/mcp.json in your project root:
{
"mcpServers": {
"gocardless": {
"command": "uvx",
"args": ["--from", "git+https://github.com/jmceleney/gocardless-mcp.git", "gocardless-mcp"],
"env": {
"GOCARDLESS_ACCESS_TOKEN": "your_access_token_here",
"GOCARDLESS_ENVIRONMENT": "sandbox"
}
}
}
}
Global configuration (available in all projects):
Create ~/.cursor/mcp.json:
{
"mcpServers": {
"gocardless": {
"command": "uvx",
"args": ["--from", "git+https://github.com/jmceleney/gocardless-mcp.git", "gocardless-mcp"],
"env": {
"GOCARDLESS_ACCESS_TOKEN": "your_access_token_here",
"GOCARDLESS_ENVIRONMENT": "sandbox"
}
}
}
}
After configuration:
- Restart Cursor
- Open the MCP settings page to verify the server is connected
- The Composer Agent will automatically use GoCardless tools when relevant
Other MCP Clients
For any MCP client that supports stdio transport:
# Make sure environment variables are set
export GOCARDLESS_ACCESS_TOKEN="your_token_here"
export GOCARDLESS_ENVIRONMENT="sandbox"
# Run the server
gocardless-mcp
The server communicates via JSON-RPC over stdin/stdout, so it won't produce output when run directly.
Data Hierarchy
GoCardless data follows this hierarchy:
- Customer (CU*) → Mandate (MD*) → Subscription (SB*) / Payment (PM*)
Mandates authorize recurring payments. Subscriptions generate recurring payments automatically.
Available Tools
Customer Tools
list_customers: List all customers (optional limit parameter)get_customer: Get a specific customer by IDcreate_customer: Create a new customer (requires email, optional given_name, family_name, company_name)
Payment Tools
list_payments: List payments (optional limit, status, subscription, mandate filters)get_payment: Get a specific payment by ID (includes links to mandate/subscription)create_payment: Create a new payment (requires amount, currency, mandate_id, optional description)
Mandate Tools
list_mandates: List mandates (optional limit and customer parameters)get_mandate: Get a specific mandate by ID (includes link to customer)
Subscription Tools
list_subscriptions: List subscriptions (optional limit and status parameters)get_subscription: Get a specific subscription by ID (includes link to mandate)get_subscription_details: Get complete subscription info including mandate and customer in one call
Payout Tools
list_payouts: List payouts (optional limit parameter)
Usage Examples
Once configured in Claude Desktop, you can ask:
- "Show me my recent GoCardless customers"
- "Get details for customer CU123"
- "Create a new customer with email test@example.com"
- "List all pending payments"
- "Show me the details of payment PM123"
Development & Testing
Testing with MCP Inspector
The MCP Inspector provides an interactive web interface to test your server:
# Run the inspector (requires Node.js)
npx @modelcontextprotocol/inspector gocardless-mcp
This will:
- Start the inspector on
http://localhost:6274 - Open your browser automatically
- Allow you to set environment variables in the UI
- Interactively test all available tools
In the Inspector:
- Set your
GOCARDLESS_ACCESS_TOKENin the environment variables section - Set
GOCARDLESS_ENVIRONMENTtosandbox - Browse available tools on the left sidebar
- Click any tool to see its schema
- Fill in parameters and click "Run" to test
Testing with a Python Client
Create a test script to programmatically test the server:
import asyncio
import os
from mcp.client.session import ClientSession
from mcp.client.stdio import StdioServerParameters, stdio_client
async def main():
server_params = StdioServerParameters(
command="gocardless-mcp",
env={
"GOCARDLESS_ACCESS_TOKEN": "your_sandbox_token",
"GOCARDLESS_ENVIRONMENT": "sandbox"
}
)
async with stdio_client(server_params) as (read, write):
async with ClientSession(read, write) as session:
await session.initialize()
# List available tools
tools = await session.list_tools()
print("Available tools:")
for tool in tools.tools:
print(f" - {tool.name}: {tool.description}")
# Test a tool
result = await session.call_tool("list_customers", {"limit": 5})
print("\nResult:", result)
asyncio.run(main())
Running Tests
# Install development dependencies
pip install -e ".[dev]"
# Run tests (when implemented)
pytest
License
MIT
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.