Sponsored by Deepsite.site

MCP YNAB Server 💰

Created By
Bulletninja10 months ago
Custom MCP server for YNAB API (TypeScript)
Content

MCP YNAB Server 💰

Welcome to the MCP server for YNAB (TypeScript version)! 🎉 This project allows you to connect Cursor (or another MCP client) to your You Need A Budget (YNAB) account to interact with your financial data directly from your editor.

1. What is this? 🤔 (Purpose)

This is an implementation of the Model Context Protocol (MCP) in TypeScript that acts as a bridge to the official YNAB API. The goal is to provide standardized tools for reading and writing YNAB data from MCP-compatible environments, allowing AI assistants like Cursor's to help you with your finances.

2. Available Tools 🛠️

This server provides the following tools, each with its own detailed documentation:

  • listBudgets: Lists your available budgets.
  • listAccounts: Lists accounts within a specified budget.
  • getAccountBalance: Fetches the current balance for a specific account.
  • listCategories: Lists categories within a specified budget.
  • getCategoryInfo: Gets detailed information about a specific category for a given month.
  • getBudgetSummary: Provides a budget summary (income, budgeted, activity) for a specific month.
  • listTransactions: Lists transactions for a budget, with filtering options (by account, category, date, etc.).
  • createTransaction: Creates a new transaction or split transaction within a budget.

See each tool's README.md for detailed information on arguments, output, and usage context.

3. Setup 🚀

  1. Clone the Repository:

    # git clone https://github.com/Bulletninja/mcp-ynab # If you haven't already
    cd mcp-ynab 
    
  2. Install Dependencies:

    npm install
    
  3. Configure Your YNAB API Token: You need a Personal Access Token from YNAB. The recommended and tested way for Cursor integration is:

    • Edit your global Cursor configuration file ~/.cursor/mcp.json.
    • Add or modify the entry for mcp-ynab, ensuring the command, args, cwd, and env are correct:
      {
        "mcpServers": {
          // ... other servers ...
          "mcp-ynab": {
            "command": "node",
            // 👇 Path to the compiled script
            "args": ["<path-to-your-project>/mcp-ynab/dist/server.js"], 
            "cwd": "<path-to-your-project>/mcp-ynab", // Path to this project
            "enabled": true,
            "env": {
              // 👇 Your YNAB token here, with the correct name!
              "YNAB_API_TOKEN": "YOUR_YNAB_TOKEN_HERE" 
            }
          }
          // ... other servers ...
        }
      }
      
    • Alternative (requires code modification): You could use a .env file in the project root, but you would need to uncomment the dotenv logic in src/server.ts and ensure it doesn't interfere with server mode.
  4. Compile the Code:

    npm run build
    

4. Usage with Cursor 💡

  1. Ensure the configuration in ~/.cursor/mcp.json is correct and "enabled": true.
  2. Restart Cursor to load the updated configuration and launch the server.
  3. Done! In Cursor's MCP settings, you should see mcp-ynab with a green dot and the list of available tools.
  4. You can now ask the AI assistant to use the tools:
    • "List my YNAB budgets"
    • "Use mcp_ynab_list_accounts with budget_id 'last-used'"
    • "What's the balance of my account X (ID: YYY) in budget Z?" (Might use mcp_ynab_get_account_balance)

5. Development 🧑‍💻

  • Run server in development mode (with hot-reload): npm run dev
  • Run tests: npm test
  • Compile for production/MCP: npm run build
  • CLI Mode (Commented Out): The logic to run commands like node dist/server.js list-budgets is commented out in src/server.ts because it interfered with Cursor's MCP server mode. You can uncomment it for local testing if needed, but remember to comment it back out and recompile for Cursor integration.

Star History Chart

Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
Amap Maps高德地图官方 MCP Server
Playwright McpPlaywright MCP server
Serper MCP ServerA Serper MCP Server
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
DeepChatYour AI Partner on Desktop
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
CursorThe AI Code Editor
Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
Tavily Mcp
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
ChatWiseThe second fastest AI chatbot™
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
WindsurfThe new purpose-built IDE to harness magic