Skip to main content
Glama
harrydaihaolin

splitwise-mcp

splitwise-mcp

CI Python License: MIT

An MCP server for Splitwise. Manage expenses, balances, settlements, groups, and comments in natural language from Claude Code, Claude Desktop, or any MCP client.

"I paid $40 for dinner, split evenly with Alex and Sam." "What's my balance with the apartment group?" "Record that I paid Sam back $15."

Tools

Category

Tools

User

whoami

Friends

list_friends

Groups

list_groups, get_group

Expenses

list_expenses, get_expense, create_expense, update_expense, delete_expense

Two-party shortcuts

split_with, lend_to, borrow_from

Settlements

record_payment

Comments

list_comments, add_comment

Two-party shortcuts

For the everyday actions between you and one friend, these wrap create_expense and resolve "you" automatically (via whoami):

  • split_with(friend_id, cost, description, i_paid=True) — 50/50 split, cent-accurate. Set i_paid=False if the friend paid.

  • lend_to(friend_id, cost, description) — you paid; the friend owes you the full amount.

  • borrow_from(friend_id, cost, description) — the friend paid; you owe them the full amount.

The fourth everyday action — skip — is just doing nothing, so there's no tool for it.

The server is a thin wrapper over the Splitwise API: the agent resolves a person's name to a user id with list_friends, then calls create_expense or record_payment. Equal splits are computed cent-accurately server-side; uneven splits are passed explicitly via shares.

Related MCP server: Splitwise MCP Server

Setup

1. Get a Splitwise API key

Go to https://secure.splitwise.com/apps, register an app, and copy your API key (a personal access token).

2. Install

Requires Python ≥ 3.10.

git clone https://github.com/harrydaihaolin/splitwise-mcp
cd splitwise-mcp
uv sync            # or: pip install -e .

3. Add to Claude Code

claude mcp add splitwise \
  --env SPLITWISE_API_KEY=your_key_here \
  -- uvx --from /absolute/path/to/splitwise-mcp splitwise-mcp

Or run the module directly:

SPLITWISE_API_KEY=your_key_here python -m splitwise_mcp

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "splitwise": {
      "command": "uvx",
      "args": ["--from", "/absolute/path/to/splitwise-mcp", "splitwise-mcp"],
      "env": { "SPLITWISE_API_KEY": "your_key_here" }
    }
  }
}

Development

uv sync --extra dev
uv run pytest

Tests use httpx.MockTransport and a fake client — no live API calls.

Design

See docs/specs/2026-06-03-splitwise-mcp-design.md.

Security

Your API key has full read/write access to your Splitwise account. It is read only from the SPLITWISE_API_KEY environment variable and never logged. Treat it like a password.

License

MIT — see LICENSE.

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

  • A
    license
    A
    quality
    D
    maintenance
    An MCP server for Splitwise that enables users to manage shared expenses, friends, and groups directly through AI assistants. It allows for creating, deleting, and listing expenses while providing tools to track net balances and group debts.
    Last updated
    8
    591
    MIT
  • F
    license
    A
    quality
    D
    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.
    Last updated
    9
    1
  • A
    license
    A
    quality
    D
    maintenance
    A Model Context Protocol server that enables AI assistants to manage Splitwise expenses using natural language, with support for voice commands, smart name matching, and advanced split configurations.
    Last updated
    7
    4
    MIT

View all related MCP servers

Related MCP Connectors

  • MCP server for Gainium — manage trading bots, deals, and balances via AI assistants

  • Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.

  • MCP server for generating rough-draft project plans from natural-language prompts.

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/harrydaihaolin/splitwise-mcp'

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