MCP Financial Advisor

by dgormly

351 downloads
Not rated
GitHub

About

A Model Context Protocol (MCP) server for financial advisory and bookkeeping, providing structured financial data and context for AI agents.

Details

Author
dgormly
Downloads
351
Categories
Finance

- Comprehensive financial data schema for accounts, transactions, and budgets
- Budgeting and financial goal tracking
- Transaction categorization and analysis
- Multi-currency support
- Report generation capabilities
- Implements MCP interfaces: context, query, and action

Clone the repository, install dependencies with npm install, initialize the database with npm run init-db, and start the MCP server with npm start. Detailed API documentation can be found in the /docs directory.

MCP Financial Advisor

A Model Context Protocol (MCP) server implementation for financial advisory and bookkeeping. This server provides structured financial data and context for AI agents, enabling them to assist with financial planning, budgeting, and analysis.

Features

- Full implementation of the Model Context Protocol (MCP)
- Comprehensive financial data schema
- Budgeting and financial goal tracking
- Transaction categorization and analysis
- Multi-currency support
- Report generation capabilities

MCP Implementation

This server implements the following MCP interfaces:

- context: Provides financial context including accounts, transactions, budgets, and goals
- query: Allows querying of financial data and generating reports
- action: Enables actions like categorizing transactions and updating budgets

Database Schema

The system uses a comprehensive SQLite database schema that includes:

- Accounts and transactions management
- Hierarchical categorization system
- Budgeting and financial goals
- Payee and tag management
- Report generation and analytics

Getting Started

1. Clone the repository
2. Install dependencies: npm install
3. Initialize the database: npm run init-db
4. Start the MCP server: npm start

API Documentation

Detailed API documentation can be found in the /docs directory.

License

MIT

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.