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
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.