About ledger-service MCP server
ledger-service MCP server provides Claude with tools to access ledger files. It supports account listings, account balances, and transaction registers for a specified year.
Key features
- 01List ledger accounts by year
- 02Retrieve an account balance
- 03View account transaction history
Use cases
- 01Checking available accounts for a year
- 02Reviewing an account balance
- 03Inspecting an account's transactions
MCP support
Exposes three ledger-management tools to MCP clients: `list-accounts`, `account-balance`, and `account-register`.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEledger-service MCP server
MCP Server for accessing and managing ledger files through Claude.
Components
Tools
The server implements three tools for ledger management:
-
list-accounts: Lists all accounts in the ledger
- Takes "year" as a required argument
- Returns formatted list of all available accounts
-
account-balance: Gets the balance for a specific account
- Takes "year" and "account" as required arguments
- Returns the current balance for the specified account
-
account-register: Shows the transaction register for an account
- Takes "year" and "account" as required arguments
- Returns detailed transaction history for the specified account
Installation
Prerequisites
- Python 3.13 or higher
uvpackage manager- Node.js and npm (for debugging)
Install from PyPI
uv pip install ledger-service
Debugging
Using the inspector to debug the server:
npx @modelcontextprotocol/inspector \
uv \
--directory /path/to/ledger-service \
run \
ledger-service

Configure Claude Desktop
Add the server configuration to Claude Desktop's config file:
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Development Configuration
"mcpServers": {
"ledger-service": {
"command": "uv",
"args": [
"--directory",
"/path/to/ledger-service",
"run",
"ledger-service"
]
}
}
Production Configuration
"mcpServers": {
"ledger-service": {
"command": "uvx",
"args": [
"ledger-service"
]
}
}
Development
Local Setup
- Clone the repository
- Create and activate a virtual environment
- Install dependencies:
The base path can be configured by modifying the LEDGER_BASE_PATH constant in server.py.
License
GNU GENERAL PUBLIC LICENSE Version 3, 29 June 2007
Comments
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.