mcpField
Y
Your Money Left The Chat

Your Money Left The Chat

Local
github.com/Rayato159AI & Agents23Updated 54w ago

About Your Money Left The Chat

Your Money Left The Chat is a Rust-based personal finance tracker that uses MCP and an LLM to log expenses from natural language, analyze spending and estimate taxes. Data is stored locally in SQLite, suiting users who want their records kept on their own machine.

Key features

  1. 01Expense logging from natural language input
  2. 02Daily, monthly and yearly summaries by category
  3. 03Graph view of spending breakdown
  4. 04Tax estimation
  5. 05Local SQLite storage

Use cases

  1. 01Logging everyday expenses through conversation
  2. 02Reviewing monthly or yearly spending by category
  3. 03Estimating tax owed on a local machine

MCP support

The project is an MCP server registered in an MCP client config, such as Claude or Ollama via mcp-cli, which calls its expense and analysis tools.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Your Money Left The Chat

📀 Demo Video

Demo Video

TL;DR

A Rust-native 🦀, SQLite-backed, LLM-powered financial tracking system

AI-powered money tracker that logs your spending, analyzes your habits, and calculates taxes. all through natural conversation.

Talk to Claude or Ollama, and the system will store everything locally using SQLite, no cloud bullshit.

🧠 Features

  • ✍️ Natural Language Input Log expenses like:

    “Spent 129 baht on KFC today” → Stored instantly

  • 📆 Smart Summaries Daily, monthly, yearly breakdowns, including category-based analytics

  • 📊 Graph View (Only Claude Can Do THIS!!!) Visualize how much of your soul goes into food every month

  • 📉 Tax Calculation Estimate how much you’ll owe Uncle Sam (or whoever)

  • 🔒 Offline & Local-First 100% yours – no internet, no accounts, no surveillance capitalism

🦀 Tech Stack

LayerTech
BackendMCP Rust SDK + SQLite + Diesel
AI InterfaceClaude / Ollama (via mcp-cli)

🔧 Getting Started

  1. Install Rust, SQLite, and Makefile

    Rust: https://www.rust-lang.org/tools/install SQLite: https://sqlite.org/download.html GNU Make: https://www.gnu.org/software/make/

  2. Clone the Repo

    https://github.com/Rayato159/your-money-left-the-chat
    cd your-money-left-the-chat
    
  3. Install Diesel CLI

     cargo install diesel_cli --no-default-features --features sqlite
    

    If you facing with the error that can't find sqlite3.lib, Please install sqlite3 on your machine first.

  4. Create Sqlite Database

    Just create file database.db in any folder you want, or you can use this command

  5. Database Setup

    Makefile:

    make migrate-up
    

    Or using cargo as original

    diesel migrate run
    
  6. Build the Project

    Makefile:

     make build-release
    

    Or using cargo as original

    cargo build --release --bin your_money_left_the_chat
    
  7. Edit the config file

    Find the config.json, of your MCP agent then add this

    Windows:

    {
      "mcpServers": {
        "money": {
          "command": "PATH-TO/your-money-left-the-chat/target/release/your_money_left_the_chat.exe",
          "args": ["PATH-TO/database.db"]
        }
      }
    }
    

    Linux/MacOS:

    {
      "mcpServers": {
        "money": {
          "command": "PATH-TO/your-money-left-the-chat/target/release/your_money_left_the_chat",
          "args": ["PATH-TO/database.db"]
        }
      }
    }
    
  8. Chatting with your dude (MCP Agent):

     You: "Hey, I spent 129 baht on KFC today"
     MCP Agent: "Got it! I've logged that expense for you. Anything else?"
    

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.