Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Finance Tracking MCP Add a $45 fuel expense to transportation"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A small MCP server for tracking personal expenses, built with FastMCP and SQLAlchemy on top of SQLite.
Tool | Description |
| Add a new expense (title, amount, category, optional date and note). Defaults to today's date. |
| Update an existing expense by ID — only the fields you pass are changed. |
| Delete an expense by ID. Returns the deleted record. |
| Totals and a per-category breakdown, optionally filtered by category and/or month ( |
Related MCP server: Expense Tracker MCP Server
URI | Description |
| The category list from |
Python 3.12+
uv run main.pyThe server creates expenses.db next to main.py on first run. That file is gitignored, so your data stays local.
Add the server to your MCP client config, for example:
{
"mcpServers": {
"finance-tracking": {
"command": "uv",
"args": ["run", "--directory", "/path/to/finance-tracking-mcp", "main.py"]
}
}
}main.py # MCP server: tools, resource, and SQLAlchemy models
categories.json # Category list exposed via the expense://categories resource
pyproject.toml # Project metadata and dependenciesAdd a new expense entry to the database.
Inputs: title (required), amount (required), category (required), date, +1 more. Returns: object
Edit an existing expense by ID. Only pass the fields you want to change.
Inputs: expense_id (required), date, note, title, +2 more. Returns: object
Get a spending summary, optionally filtered by category and/or month.
Inputs: month, category. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool serves a clearly distinct purpose: summarizing expenses, adding new ones, and editing existing ones. There is no overlap or ambiguity in their functions.
Two tools follow a verb_noun pattern (add_expense, edit_expense), while expense_summary deviates slightly as a noun-first name. This minor inconsistency does not hinder readability.
With only 3 tools, the server is well-scoped for a focused expense tracking purpose. Each tool earns its place with no redundancy or excess.
The server covers add, edit, and summary, but lacks a delete operation and a way to retrieve individual expense details. This represents a notable gap in lifecycle coverage.
Personal finance tracker — log transactions, view summaries, and browse a dashboard
Track expenses from your AI chat: log, categorize, monthly CSV reports. All data is local.
Personal finance ledger: log expenses, track bills and cards, import statements.
Personal finance tracker: log expenses and income, track EMIs, debts, subscriptions and bills.
