Splitwise MCP Server
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.
README
Splitwise MCP Server
A Model Context Protocol (MCP) server that integrates with Splitwise. Connect your AI assistant (Claude, Cursor, etc.) to manage Splitwise expenses using natural language — with voice support!
How It Works
flowchart LR
Client[Claude / Cursor] -->|MCP| Server[splitwise-mcp]
Server -->|audio| Deepgram[Deepgram STT]
Deepgram -->|text| Gemini[Gemini 3 Flash]
Gemini -->|action| Splitwise[Splitwise API]
Features
| Tool | Description |
|---|---|
voice_command |
Send audio → Deepgram transcribes → Gemini processes → Splitwise executes |
text_command |
Send text → Gemini processes → Splitwise executes |
add_expense |
Add expenses with support for groups, percentages, exclusions, and specific payers |
delete_expense |
Delete an expense by ID |
list_friends |
List your Splitwise friends |
configure_splitwise |
Configure API credentials |
login_with_token |
Login with OAuth2 token |
Smart Name Matching: If Deepgram transcribes "Humeet" but your friend is "Sumeet", Gemini will ask for clarification instead of guessing.
Advanced Splits
- Percentages: "Split 40% for me and 60% for Alice"
- Groups: "Add to Apartment group" (Auto-fetches members)
- Exclusions: "Add to Apartment but exclude Bob"
- Payer: "Alice paid $50"
- Deletion: "Delete expense 12345"
Installation
Option 1: Install from PyPI (Recommended)
pip install splitwise-mcp
Option 2: Install from Source
-
Clone the repository:
git clone https://github.com/hubshashwat/the-splitwise-mcp.git cd the-splitwise-mcp -
Create and activate a virtual environment:
python3 -m venv .venv source .venv/bin/activate -
Install the package:
pip install -e .
Configuration
You'll need API keys depending on which features you want:
Required (Core Splitwise Features)
- Splitwise API Keys (https://secure.splitwise.com/apps/new)
- Register a new application
- Get: Consumer Key, Consumer Secret, and API Key
- Required for:
add_expense,list_friends,delete_expense
Optional (AI Features)
-
Gemini API Key (https://aistudio.google.com/) - Optional
- Create API key (free tier available)
- Model: Uses Gemini 3.0 Flash - ensure your API key has access to this model
- Required for:
text_command(natural language processing)
-
Deepgram API Key (https://console.deepgram.com/) - Optional
- Sign up and get API key (free tier available)
- Required for:
voice_command(audio transcription)
Summary:
- Text-only users: Need Splitwise + Gemini keys (skip Deepgram)
- Voice users: Need all 5 keys
- Basic API users: Only need 3 Splitwise keys
Set environment variables in your shell or add to your Claude Desktop config (see below).
Usage
You can use this server in two ways:
Option A: Standalone Terminal Agent (No Claude Required!) 🖥️
Run the voice/text agent directly in your terminal:
# Install the package
pip install splitwise-mcp
# Download the agent script
curl -O https://raw.githubusercontent.com/hubshashwat/the-splitwise-mcp/main/run_agent.py
# Set environment variables
export SPLITWISE_CONSUMER_KEY="your_key"
export SPLITWISE_CONSUMER_SECRET="your_secret"
export SPLITWISE_API_KEY="your_api_key"
export GEMINI_API_KEY="your_gemini_key"
export DEEPGRAM_API_KEY="your_deepgram_key"
# Run the agent
python run_agent.py
Commands:
vorvoice- Record 10 seconds of audio and process ittortext- Type your commandqorquit- Exit
Example session:
🤖 Splitwise Voice Agent
Enter command (voice/text/quit): t
Enter request: Add expense of $50 with John for dinner
⚠️ Proposed Action:
Function: add_expense
Args: {
"description": "dinner",
"cost": 50.0,
"split_with": ["John"]
}
Proceed? (yes/edit/cancel): yes
✅ Expense added!
Option B: With MCP Clients 💬
This server uses stdio transport and works with all MCP-compatible clients:
Claude Desktop
Add to your config:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"splitwise": {
"command": "full path of python",
"args": ["-m", "splitwise_mcp.server"],
"env": {
"SPLITWISE_CONSUMER_KEY": "your_consumer_key",
"SPLITWISE_CONSUMER_SECRET": "your_consumer_secret",
"SPLITWISE_API_KEY": "your_api_key",
"GEMINI_API_KEY": "your_gemini_key",
"DEEPGRAM_API_KEY": "your_deepgram_key"
}
}
}
}
Note: If
splitwise-mcpconsole command is available, you can use"command": "splitwise-mcp"without args instead.
Then in Claude: "Add an expense of $50 with John for dinner"
Claude CLI
Use the same config format with claude-cli --mcp-config.
Cursor / VS Code (Antigravity, Cline, Continue.dev)
Add to your MCP settings (.vscode/settings.json or Cursor settings):
{
"mcp.servers": {
"splitwise": {
"command": "full path of python",
"args": ["-m", "splitwise_mcp.server"],
"env": {
"SPLITWISE_CONSUMER_KEY": "your_consumer_key",
"SPLITWISE_CONSUMER_SECRET": "your_consumer_secret",
"SPLITWISE_API_KEY": "your_api_key",
"GEMINI_API_KEY": "your_gemini_key",
"DEEPGRAM_API_KEY": "your_deepgram_key"
}
}
}
}
Then you can ask your AI assistant: "Use Splitwise to add an expense..."
Other MCP Clients
This server is compatible with any MCP client supporting stdio transport. Use the same configuration pattern.
Note: If you installed from source instead of pip, use the full path to the executable:
- macOS/Linux:
"/path/to/the-splitwise-mcp/.venv/bin/splitwise-mcp" - Windows:
"C:\\path\\to\\the-splitwise-mcp\\.venv\\Scripts\\splitwise-mcp.exe"
Remote Access (SSE)
To run the MCP server over HTTP for remote clients:
.venv/bin/uvicorn splitwise_mcp.sse:app --host 0.0.0.0 --port 8000
Connect via: http://YOUR_IP:8000/sse
Development
Run tests:
.venv/bin/python tests/test_logic.py
Troubleshooting
Microphone Issues (macOS)
If the agent says "Recording finished" immediately but captures no audio (Volume: 0.0), your terminal likely lacks microphone permission.
- Go to System Settings > Privacy & Security > Microphone.
- Enable access for your terminal app (Terminal, iTerm, VS Code, etc.).
- Restart your terminal for changes to take effect.
License
MIT
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。