splitwise-mcp

splitwise-mcp

Enables natural language management of Splitwise expenses, groups, and friends via the Model Context Protocol, with dual authentication and fuzzy name resolution.

Category
访问服务器

README

Splitwise MCP Server

A Model Context Protocol (MCP) server for Splitwise, enabling AI agents to manage expenses, groups, and friends with natural language.

Features

  • Full API Access: Manage expenses, groups, friends, and comments.
  • Natural Language Resolution: Fuzzy matching for names ("John" -> "John Smith") and groups.
  • Dual Auth: Supports both OAuth 2.0 (recommended) and API Keys.
  • Smart Caching: Optimizes performance for static data like categories and currencies.

Installation

# From PyPI (when published)
pip install splitwise-mcp-server

# From Source
git clone https://github.com/tarunn2799/splitwise-mcp-server
cd splitwise-mcp-server
pip install -e .

Configuration

See SETUP.md for detailed authentication and configuration instructions.

Quick Config

Run the included setup script:

python -m splitwise_mcp_server.oauth_setup

Use the keys provided there, and add all three to your mcp.json:

{
  "mcpServers": {
    "splitwise": {
      "command": "python",
      "args": ["-m", "splitwise_mcp_server"],
      "env": {
        "SPLITWISE_OAUTH_ACCESS_TOKEN": "your_token_here"
      }
    }
  }
}

Get your Auth Keys You can get your Consumer Key and Secret by registering an app at https://secure.splitwise.com/apps.

IMPORTANT: Using a Virtual Environment? If you installed the package in a venv or Conda environment, you must use the absolute path to the python executable in your config.

"command": "/absolute/path/to/venv/bin/python"

See SETUP.md for details.

Usage

The server enables natural language interactions with your Splitwise data.

Examples:

  • "What's my current balance?"
  • "Split a $50 dinner with Sarah."
  • "Use the receipt I uploaded to split the dinner between Manav and me."
  • "Show me expenses from last month."
  • "Create a group called 'Ski Trip' with Mike."

Tools

See TOOLS.md for detailed documentation.

User Tools

  • get-current-user: Get authenticated user information
  • get-user: Get information about a specific user

Expense Tools

  • create-expense: Create a new expense with splits
  • get-expenses: List expenses with optional filters
  • get-expense: Get detailed expense information
  • update-expense: Update an existing expense
  • delete-expense: Delete an expense

Group Tools

  • get-groups: List all groups
  • get-group: Get detailed group information
  • create-group: Create a new group
  • delete-group: Delete a group
  • add-user-to-group: Add a user to a group
  • remove-user-from-group: Remove a user from a group

Friend Tools

  • get-friends: List all friends
  • get-friend: Get detailed friend information

Resolution Tools

  • resolve-friend: Fuzzy match friend names to user IDs
  • resolve-group: Fuzzy match group names to group IDs
  • resolve-category: Fuzzy match category names to category IDs

Comment Tools

  • create-comment: Add a comment to an expense
  • get-comments: Get all comments for an expense
  • delete-comment: Delete a comment

Utility Tools

  • get-categories: Get all expense categories
  • get-currencies: Get all supported currencies

Arithmetic Tools

  • add: Add multiple numbers
  • subtract: Subtract numbers
  • multiply: Multiply numbers
  • divide: Divide numbers
  • modulo: Calculate remainder

Development

# Setup
git clone https://github.com/tarunn2799/splitwise-mcp-server
cd splitwise-mcp-server
python -m venv venv
source venv/bin/activate
pip install -e ".[dev]"

# Test
pytest

License

MIT License. See LICENSE for details.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选