splitwise-mcp
An MCP server for Splitwise that lets you manage expenses, balances, settlements, groups, and comments in natural language from any MCP client.
README
splitwise-mcp
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. Seti_paid=Falseif 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.
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.
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.