Skip to main content
Glama
Gotha8972

Splitwise MCP Server

by Gotha8972

Splitwise MCP Server

A custom MCP (Model Context Protocol) server that connects to your Splitwise account. Query your expenses, see who owes whom, and get category-wise spending breakdowns — all from your MCP client (Claude Desktop, Gemini CLI, etc).

Read-only · INR only

Features

Tool

Description

get_my_profile

Your Splitwise user info

get_friends_balances

Friends with INR balances (who owes whom)

get_groups

All groups with members and balances

get_expenses

Fetch expenses with date/group/friend filters

get_spending_by_category

⭐ Category-wise spending breakdown

get_category_list

All Splitwise categories & subcategories

Related MCP server: splitwise-mcp

Setup

1. Get Splitwise API Credentials

  1. Go to https://secure.splitwise.com/oauth_clients

  2. Click Register your application

  3. Fill in any name/description/URL (they can be placeholders)

  4. After registering, you'll see your Consumer Key and Consumer Secret

  5. On the same page, you'll find your API Key — this is tied to your personal account

2. Configure Credentials

Copy the example env file and fill in your credentials:

cp .env.example .env

Edit .env:

SPLITWISE_CONSUMER_KEY=your_consumer_key
SPLITWISE_CONSUMER_SECRET=your_consumer_secret
SPLITWISE_API_KEY=your_api_key

3. Install Dependencies

# Create a virtual environment (recommended)
python -m venv .venv

# Activate it
# Windows:
.venv\Scripts\activate
# macOS/Linux:
source .venv/bin/activate

# Install
pip install -e .

4. Test with MCP Inspector

fastmcp dev inspector server.py

This opens a web UI where you can test each tool interactively.

5. Configure Your MCP Client

Claude Desktop

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "splitwise": {
      "command": "python",
      "args": ["c:\\Project\\Spark MCP\\server.py"],
      "env": {
        "SPLITWISE_CONSUMER_KEY": "your_key",
        "SPLITWISE_CONSUMER_SECRET": "your_secret",
        "SPLITWISE_API_KEY": "your_api_key"
      }
    }
  }
}

Gemini CLI

Add to your ~/.gemini/settings.json:

{
  "mcpServers": {
    "splitwise": {
      "command": "python",
      "args": ["c:\\Project\\Spark MCP\\server.py"],
      "env": {
        "SPLITWISE_CONSUMER_KEY": "your_key",
        "SPLITWISE_CONSUMER_SECRET": "your_secret",
        "SPLITWISE_API_KEY": "your_api_key"
      }
    }
  }
}

Example Prompts

Once configured, try asking your AI assistant:

  • "How much have I spent this month?"

  • "Show me my spending by category for the last 3 months"

  • "Who owes me money?"

  • "What are my recent expenses in the Flat group?"

  • "What's my total spending on food this year?"

License

MIT

A
license - permissive license
-
quality - not tested
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • F
    license
    A
    quality
    C
    maintenance
    A standalone MCP server that provides complete access to the Splitwise API, enabling natural language management of expenses, groups, friends, and notifications in MCP-compatible clients like Claude Desktop and VS Code Copilot.
    9
    1
  • A
    license
    -
    quality
    B
    maintenance
    An MCP server for Splitwise that lets you manage expenses, balances, settlements, groups, and comments in natural language from any MCP client.
    MIT
  • A
    license
    -
    quality
    C
    maintenance
    MCP server that exposes every endpoint from Splitwise's public self-serve API docs as MCP tools, covering 27 operations for managing expenses, users, and groups.
    289
    MIT

View all related MCP servers

Related MCP Connectors

  • Read-only MCP server for ClassQuill, a tutoring-business-management platform.

  • Hosted remote MCP server for YNAB on Cloudflare Workers with OAuth

  • Hosted MCP server for Mini Accountant: invoices, expenses, customers, analytics, tax estimates.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Gotha8972/MCP-Server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server