mcp-expense-tracker
Enables tracking personal expenses by adding, listing, deleting, and summarizing expenses by day or month, stored locally in a JSON file.
README
mcp-expense-tracker
An MCP (Model Context Protocol) server for tracking expenses. Expenses are stored in a local JSON file, and the server exposes tools for adding expenses and summarizing totals by day or month.
Two equivalent implementations are included:
src/— TypeScript/Node, stdio transport. Use this with Claude Code or Claude Desktop.server.py— Python (FastMCP). Use this to deploy on FastMCP Cloud so it's reachable as a remote connector from claude.ai.
Tools
- add_expense — record an expense (
amount,category, optionaldescription, optionaldatedefaulting to today) - list_expenses — list expenses, optionally filtered by
start_date,end_date,category - delete_expense — delete an expense by
id - summarize — get the total (and per-category breakdown) for a
day,month, oralltime, anchored on an optionaldate
Deploy on FastMCP Cloud (for claude.ai)
FastMCP Cloud deploys directly from this GitHub repo. When it asks for an entrypoint, use:
server.py
(FastMCP Cloud auto-detects the mcp object in server.py; you'd only need server.py:mcp if the variable were named something else.) It installs requirements.txt automatically. Once deployed, add the resulting https://<your-app>.fastmcp.app/mcp URL as a custom connector in claude.ai's connector settings.
Storage caveat: server.py stores expenses in a local data/expenses.json file. Confirm your FastMCP Cloud plan gives that container a persistent disk — if storage is ephemeral/rebuilt on redeploy, expenses will reset. If you hit that, swap server.py's file-backed storage for a hosted database.
Node/TypeScript setup
npm install
npm run build
Run standalone
npm start
The server communicates over stdio, so it's meant to be launched by an MCP client rather than used directly in a terminal.
Use with Claude Code
claude mcp add expense-tracker -- node /absolute/path/to/mcp-tracker/build/index.js
Use with Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"expense-tracker": {
"command": "node",
"args": ["/absolute/path/to/mcp-tracker/build/index.js"]
}
}
}
Run the Python version locally
pip install -r requirements.txt
python server.py
Data storage
Expenses are stored in data/expenses.json (created automatically). Set EXPENSE_DATA_DIR to change where data is stored. This applies to both implementations.
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.
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.
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.
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.