Splitwise MCP Server

A Model Context Protocol (MCP) server that enables AI assistants like Claude to manage Splitwise expenses with atomic duplicate prevention.

Features

• Atomic Duplicate Prevention: Reserve-then-create pattern prevents accidental duplicate expenses from race conditions
• Smart Duplicate Detection: Fuzzy matching on description, amount, and date within configurable windows
• Local SQLite Cache: Fast duplicate checks without excessive API calls
• Flexible Split Ratios: Support for any split percentage (50/50, 75/25, 100/0, etc.)
• Order ID Tracking: Link expenses back to source orders (Amazon, Instacart, etc.) for traceability

Requirements

• Python 3.10+
• Splitwise API key
• MCP-compatible client (Claude Code, etc.)

Installation

# Clone the repository
git clone https://github.com/vishnujayvel/splitwise-mcp.git
cd splitwise-mcp

# Install in development mode
pip install -e .

# Or install with dev dependencies for testing
pip install -e .[dev]

Configuration

The server supports multiple configuration methods, checked in this order:

Option 1: Environment Variables (Recommended for production)

export SPLITWISE_API_KEY="your_api_key"
export SPLITWISE_GROUP_ID="your_group_id"
export SPLITWISE_PAYER_ID="your_user_id"
export SPLITWISE_PARTNER_ID="partner_user_id"

# Optional: custom config file path
export SPLITWISE_CONFIG_PATH="/path/to/config.json"

# Optional: logging level (DEBUG, INFO, WARNING, ERROR)
export LOG_LEVEL="INFO"

# Optional: custom cache database path
export SPLITWISE_CACHE_PATH="./splitwise_cache.db"

Option 2: Configuration File

Create a config.json file (see config.example.json):

{
  "splitwise": {
    "api_key": "YOUR_SPLITWISE_API_KEY",
    "group_id": "YOUR_GROUP_ID",
    "payer_id": "YOUR_USER_ID",
    "partner_id": "PARTNER_USER_ID"
  }
}

Getting Your Splitwise Credentials

1. API Key:

   • Go to https://secure.splitwise.com/apps
   • Click "Register your application"
   • Fill in the application details
   • Copy the API key

2. User IDs and Group ID:

   • Go to https://secure.splitwise.com/api/v3.0/get_current_user (with authentication)
   • Or use the Splitwise API to query your groups and members
   • Your user ID and your partner's user ID are in the group members list

Usage with Claude Code

Add to your .mcp.json file:

{
  "mcpServers": {
    "splitwise": {
      "command": "python",
      "args": ["-m", "splitwise_mcp.server"],
      "cwd": "/path/to/splitwise-mcp/src",
      "env": {
        "SPLITWISE_API_KEY": "your_api_key",
        "SPLITWISE_GROUP_ID": "your_group_id",
        "SPLITWISE_PAYER_ID": "your_user_id",
        "SPLITWISE_PARTNER_ID": "partner_user_id"
      }
    }
  }
}

MCP Tools

splitwise_check_duplicate

Check if an expense would be a duplicate based on description, amount, and date similarity.

Input:

{
  "description": "Amazon - Electronics",
  "amount": 49.99,
  "date": "2024-12-30",
  "group_id": "YOUR_GROUP_ID"
}

Output:

{
  "is_duplicate": false,
  "reason": "No duplicate found",
  "existing_expense_id": null,
  "similarity_score": 0.0
}

splitwise_reserve_expense

Atomically reserve an expense slot to prevent race conditions. Must be called before creating an expense.

Input:

{
  "description": "Amazon - Electronics",
  "amount": 49.99,
  "date": "2024-12-30",
  "group_id": "YOUR_GROUP_ID",
  "order_id": "123-4567890-1234567"
}

Output:

{
  "reservation_id": "temp_abc123def456",
  "expires_at": "2024-12-30T12:05:00",
  "is_duplicate": false,
  "reason": "Reservation created successfully",
  "existing_expense_id": null
}

splitwise_create_expense

Create an expense in Splitwise and confirm the reservation.

Input:

{
  "reservation_id": "temp_abc123def456",
  "description": "Amazon - Electronics",
  "amount": 49.99,
  "date": "2024-12-30",
  "group_id": "YOUR_GROUP_ID",
  "payer_id": "YOUR_USER_ID",
  "partner_id": "PARTNER_USER_ID",
  "order_id": "123-4567890-1234567",
  "split_ratio": "50/50"
}

Output:

{
  "status": "created",
  "expense_id": "987654321",
  "payer_owes": 24.99,
  "partner_owes": 25.00,
  "total": 49.99,
  "url": "https://secure.splitwise.com/#/expenses/987654321"
}

splitwise_sync_cache

Sync the local cache with Splitwise API. Fetches recent expenses and updates the cache.

Input:

{
  "group_id": "YOUR_GROUP_ID",
  "since_date": "2024-12-01",
  "limit": 100
}

Output:

{
  "synced_count": 15,
  "last_sync_at": "2024-12-30T12:00:00",
  "cache_size": 42
}

splitwise_get_expenses

Query expenses from the local cache (fast, no API call).

Input:

{
  "group_id": "YOUR_GROUP_ID",
  "start_date": "2024-12-01",
  "end_date": "2024-12-31"
}

Output:

{
  "expenses": [
    {
      "id": "987654321",
      "description": "Amazon - Electronics",
      "amount": 49.99,
      "date": "2024-12-30",
      "payer_owes": 24.99,
      "partner_owes": 25.00
    }
  ],
  "total_count": 1
}

splitwise_delete_expense

Delete an expense from Splitwise and remove it from the cache.

Input:

{
  "expense_id": "987654321",
  "group_id": "YOUR_GROUP_ID"
}

Output:

{
  "status": "deleted",
  "expense_id": "987654321"
}

splitwise_find_by_order_id

Find an expense by order ID (most reliable duplicate detection method).

Input:

{
  "order_id": "123-4567890-1234567"
}

Output:

{
  "found": true,
  "expense": {
    "expense_id": "987654321",
    "description": "Amazon - Electronics",
    "cost": 49.99,
    "date": "2024-12-30",
    "order_id": "123-4567890-1234567",
    "group_id": "YOUR_GROUP_ID"
  }
}

Known Limitations

This is an early release optimized for two-person expense splitting (couples, roommates). The following features are not yet supported:

Contributions welcome for any of these features!

Troubleshooting

"Missing required configuration fields"

Ensure all required environment variables or config file fields are set:

• SPLITWISE_API_KEY / api_key
• SPLITWISE_GROUP_ID / group_id
• SPLITWISE_PAYER_ID / payer_id
• SPLITWISE_PARTNER_ID / partner_id

"Splitwise API error 401"

Your API key is invalid or expired. Generate a new one at https://secure.splitwise.com/apps

"Reservation expired"

Reservations expire after 5 minutes. Create the expense immediately after reserving, or reserve again.

Duplicate not detected

1. Run splitwise_sync_cache to update the local cache
2. Check that the expense date is within the duplicate detection window (default: 7 days)

Development

# Install dev dependencies
pip install -e .[dev]

# Run tests
PYTHONPATH=src pytest tests/ -v

# Run the server for testing
python -m splitwise_mcp.server

License

MIT License - see LICENSE file for details.