splitwise-mcp
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.
README
Check out my other MCP tools
splitwise-mcp
MCP server that exposes every endpoint from Splitwise's public self-serve API docs as MCP tools.
Current coverage from spec/paths/index.yaml: 27 API operations.
Authentication
Splitwise uses Bearer authentication for API calls. This server accepts any of these env vars:
SPLITWISE_API_KEY(recommended for personal use; easiest path)SPLITWISE_ACCESS_TOKENSPLITWISE_OAUTH_ACCESS_TOKENSPLITWISE_BEARER_TOKEN
If none are set, tool calls fail with an auth error.
Which key/credential do you need?
- Personal scripts/single account: create a Splitwise app and use its personal API key as a Bearer token.
- Multi-user app: use OAuth 2.0 Authorization Code (client key + client secret) to get user access tokens, then pass the access token as Bearer.
- OAuth 1.0 is not used by the current docs.
Run with Bunx
Bunx expects a package + executable. For path/GitHub sources, use -p and then the bin name (splitwise-mcp).
Published package (npm):
SPLITWISE_API_KEY=your_token bunx splitwise-mcp
Local path source:
SPLITWISE_API_KEY=your_token bunx -p /absolute/path/to/splitwise-mcp splitwise-mcp
GitHub source:
SPLITWISE_API_KEY=your_token bunx -p github:adinschmidt/splitwise-mcp splitwise-mcp
Note: bunx /path/to/repo is not supported by Bun 1.3.x. Use -p form above.
MCP Client Config Example
Using published npm package:
{
"mcpServers": {
"splitwise": {
"command": "bunx",
"args": ["splitwise-mcp"],
"env": {
"SPLITWISE_API_KEY": "your_splitwise_token"
}
}
}
}
Using a local checkout:
{
"mcpServers": {
"splitwise": {
"command": "bunx",
"args": ["-p", "/absolute/path/to/splitwise-mcp", "splitwise-mcp"],
"env": {
"SPLITWISE_API_KEY": "your_splitwise_token"
}
}
}
}
Tool Naming
Each API path is mapped to one tool name by path normalization.
Examples:
/get_current_user->get_current_user/get_user/{id}->get_user_id/delete_expense/{id}->delete_expense_id
There is also a helper tool:
splitwise_list_operations: lists all registered Splitwise operations.
Request Shape for Tools
Every tool accepts:
- Path/query parameters as top-level fields (for example
id,limit,offset) bodyfor JSON request bodies (when the endpoint supports/needs a body)- For best results, pass
bodyas an object. If you pass a string, use a JSON object string or URL-encoded form string.
Spec Sync
To refresh specs from Splitwise official docs repo:
bun run sync-spec
Then restart the MCP server.
Sources
- Splitwise API docs: https://dev.splitwise.com/
- Splitwise API OpenAPI source: https://github.com/splitwise/api-docs
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。