personal-finance-mcp
A comprehensive MCP server for managing personal finances, enabling users to track expenses, manage budgets, monitor financial goals, and analyze spending patterns through an AI assistant. All data is stored locally in SQLite for complete privacy.
README
Personal Finance MCP Server
A comprehensive Model Context Protocol (MCP) server for personal finance and budget management. Track expenses, manage budgets, monitor financial goals, and gain insights into your spending patterns through AI assistants.
This fork adds a stateless
streamable-httptransport and Docker support for remote/gateway deployments, in addition to the original stdio mode. See HTTP / Docker Deployment below.
🚀 Features
6 Powerful Tools
- add_transaction - Record income and expenses with categorization
- get_spending_summary - Analyze spending patterns by time period and category
- manage_budget - Create and track monthly budget limits with overspend alerts
- track_financial_goal - Set and monitor progress toward financial goals
- analyze_spending_patterns - Deep insights into spending behavior and trends
- manage_accounts - Handle multiple accounts (checking, savings, credit, etc.)
Key Capabilities
- 💰 Transaction Management: Record income and expenses with rich metadata
- 📊 Budget Tracking: Set monthly limits and get real-time budget alerts
- 🎯 Goal Setting: Track progress toward savings and financial milestones
- 📈 Smart Analytics: Monthly trends, category breakdowns, and spending insights
- 💳 Multi-Account Support: Manage checking, savings, credit, investment accounts
- 🔒 Local Data: All data stored locally in SQLite - complete privacy
🎨 Pricing Note
The upstream project describes this as a freemium server with a $12/month premium tier (unlimited transactions/accounts, advanced analytics, multi-currency, etc.). As of this fork, no license check, payment gating, or usage limiting is implemented in code — all 6 tools run fully unrestricted regardless of tier. Treat the free/premium tier descriptions as aspirational/marketing text only.
📦 Installation
npm install
🔧 Setup
Claude Desktop (stdio)
Add to your claude_desktop_config.json:
{
"mcpServers": {
"personal-finance": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/personal-finance-mcp/src/index.js"],
"env": {
"FINANCE_DB_PATH": "/ABSOLUTE/PATH/TO/finance.db"
}
}
}
}
🌐 HTTP / Docker Deployment
For remote/gateway use (e.g. an MCP hub), this fork ships an Express-based HTTP bridge (src/http-server.js) using StreamableHTTPServerTransport, stateless (no session ID required — each request is handled independently).
Docker
docker build --platform linux/amd64 -t personal-finance-mcp .
docker run -d -p 8000:8000 \
-e FINANCE_DB_PATH=/data/finance.db \
-v $(pwd)/data:/data \
personal-finance-mcp
The server listens on POST /mcp (JSON-RPC 2.0, Accept: application/json, text/event-stream) and exposes GET /health for liveness checks.
Running the HTTP bridge directly
FINANCE_DB_PATH=/path/to/finance.db PORT=8000 node src/http-server.js
Environment Variables
| Variable | Required | Description |
|---|---|---|
FINANCE_DB_PATH |
No | SQLite file path (default: ./finance.db in the working directory). Set this to a mounted volume path for persistence across container restarts. |
PORT |
No | HTTP port for streamable-http mode (default: 8000) |
💡 Usage Examples
Record a Transaction
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.