Quickbooks Mcp Server

by nikhilgy

293 downloads
Not rated
GitHub

About

This repository provides an MCP (Modular Command Platform) server for seamless interaction with all public QuickBooks APIs. It is designed to be integrated with Claude Desktop, enabling AI assistants to query, retrieve, and manipulate QuickBooks data programmatically.

Details

Author
nikhilgy
Downloads
293
Categories
Cloud Service, Finance, Other

- Integrates Claude Desktop with QuickBooks API.
- Dynamically downloads latest QuickBooks API documentation.
- Provides tools for accounts, bills, and customers.
- Uses uv for fast package management.
- Requires Python 3.10 or higher.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Quickbooks Mcp Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install Python 3.10+ and uv, then configure Claude Desktop by editing claude_desktop_config.json with the QuickBooks MCP server command and required environment variables. Launch Claude Desktop and use natural language commands like "Get all accounts from QuickBooks."

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "quickbooks mcp server": {
            "QuickBooks": {
                "command": "<home_path>/.local/bin/uv",
                "args": [
                    "--directory",
                    "<absolute_path_to_quickbooks_mcp_folder>",
                    "run",
                    "main_quickbooks_mcp.py"
                ],
                "env": {
                    "QUICKBOOKS_CLIENT_ID": "<client_id>",
                    "QUICKBOOKS_CLIENT_SECRET": "<client_secret>",
                    "QUICKBOOKS_REFRESH_TOKEN": "<refresh_token>",
                    "QUICKBOOKS_COMPANY_ID": "<company_id>"
                }
            },
            "filesystem": {
                "command": "<home_path>/.local/bin/uv",
                "args": [
                    "--directory",
                    "<absolute_path_to_quickbooks_mcp_folder>",
                    "run",
                    "filesystem.py"
                ]
            }
        }
    }
}

McpServers

{
    "QuickBooks": {
        "command": "<home_path>/.local/bin/uv",
        "args": [
            "--directory",
            "<absolute_path_to_quickbooks_mcp_folder>",
            "run",
            "main_quickbooks_mcp.py"
        ],
        "env": {
            "QUICKBOOKS_CLIENT_ID": "<client_id>",
            "QUICKBOOKS_CLIENT_SECRET": "<client_secret>",
            "QUICKBOOKS_REFRESH_TOKEN": "<refresh_token>",
            "QUICKBOOKS_COMPANY_ID": "<company_id>"
        }
    },
    "filesystem": {
        "command": "<home_path>/.local/bin/uv",
        "args": [
            "--directory",
            "<absolute_path_to_quickbooks_mcp_folder>",
            "run",
            "filesystem.py"
        ]
    }
}

Query QuickBooks data using natural language.

A secure, local-first Model Context Protocol (MCP) server to query QuickBooks data using natural language inside Claude Desktop.

This MCP Server iscertified by MCP Review.

Being listed and certified on MCP Review ensures this server adheres to MCP standards and best practices, and is trusted by the developer community.

For local development, create a.envfile in the project root with your QuickBooks credentials:

# Copy the template and fill in your actual credentials cp env_template.txt .env

Then edit the.envfile with your actual QuickBooks API credentials:

QUICKBOOKS_CLIENT_ID=your_actual_client_id QUICKBOOKS_CLIENT_SECRET=your_actual_client_secret QUICKBOOKS_REFRESH_TOKEN=your_actual_refresh_token QUICKBOOKS_COMPANY_ID=your_actual_company_id QUICKBOOKS_ENV='sandbox' or 'production'

Note:The.envfile is automatically ignored by git for security reasons.

- MacOS/Linux: curl -LsSfhttps://astral.sh/uv/install.sh| sh
- Windows: powershell -ExecutionPolicy ByPass -c "irm
https://astral.sh/uv/install.ps1| iex"
- Download
Claude Desktop.
- Launch Claude and go to Settings > Developer > Edit Config.
- Modifyclaude_desktop_config.jsonwith:

{ "mcpServers": { "QuickBooks": { "command": "uv", "args": [ "--directory", "<absolute_path_to_quickbooks_mcp_folder>", "run", "main_quickbooks_mcp.py" ] } } }

The first time you open Claude Desktop with these setting it may take 10-20 seconds before the QuickBooks tools appear in the interface due to the installation of the required packages and the download of the most recent QuickBooks API documentation.

Everytime you launch Claude Desktop, the most recent QuickBooks API tools are made available to your AI assistant.

Step 3. Launch Claude Desktop and let your assistant help you

Get all bills from QuickBooks created after 2024-01-01.

Realtime and Historical Exchange Rate Data, FX pairs, bid/ask, OHLC and Crypto prices

Interact with Twelve Data APIs to access real-time and historical financial market data for your AI agents.

Interact with the Alpaca trading API for stock trading, account management, and market data using LLMs.

Interact with Alpaca's market data and brokerage services via its API.

Streams real-time Binance Alpha token prices and liquidity data for AI agents and workflows.

Access Alpha Vantage financial data APIs to get real-time and historical stock data, forex rates, and cryptocurrency information.

Access real-time and historical stock market data from the Alpha Vantage API.

Access real-time financial data, including stock prices, forex rates, and cryptocurrencies from Alpha Vantage.

Provides real-time financial market data using the Alpha Vantage API.

A read-only server to query live TaxJar data, powered by the CData JDBC Driver.

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.