Sponsored by Deepsite.site

ynab-mcp-server

Created By
MCP-Mirror8 months ago
Mirror of
Content

ynab-mcp-server

A Model Context Protocol (MCP) server built with mcp-framework. This MCP provides tools for interacting with your YNAB budgets setup at https://ynab.com

In order to have an AI interact with this tool, you will need to get your Personal Access Token from YNAB: https://api.ynab.com/#personal-access-tokens. When adding this MCP server to any client, you will need to provide your personal access token as YNAB_API_TOKEN. This token is never directly sent to the LLM. It is stored privately in an environment variable for use with the YNAB api.

Setup

Specify env variables:

  • YNAP_API_TOKEN (required)
  • KNOWLEDGE_DIR (optional) - directory where knowledge file should be stored. Defaults to data directory where the server is running.
  • KNOWLEDGE_FILE (optional) - name of knowledge filed. Defaults to server-knowledge.json

Goal

The goal of the project is to be able to interact with my YNAB budget via an AI conversation. There are a few primary workflows I want to enable:

Workflows:

First time setup

  • be prompted to select your budget from your available budgets. If you try to use another tool first, this prompt should happen asking you to set your default budget.
    • Tools needed: ListBudgets, SetBudget

Manage overspent categories

Adding new transactions

Approving transactions

Check total monthly spending vs total income

Auto-distribute ready to assign funds based on category targets

Current state

Available tools:

  • ListBudgets - lists available budgets on your account
  • BudgetSummary - provides a summary of categories that are underfunded and accounts that are low
  • GetUnapprovedTransactions - retrieve all unapproved transactions
  • CreateTransaction - creates a transaction for a specified budget and account.
    • example prompt: Add a transaction to my Ally account for $3.98 I spent at REI today
    • requires GetBudget to be called first so we know the account id

Next:

Quick Start

# Install dependencies
npm install

# Build the project
npm run build

Project Structure

ynab-mcp-server/
├── src/
│   ├── tools/        # MCP Tools
│   └── index.ts      # Server entry point
├── package.json
└── tsconfig.json

Adding Components

The YNAB sdk describes the available api endpoints: https://github.com/ynab/ynab-sdk-js.

YNAB open api specification is here: https://api.ynab.com/papi/open_api_spec.yaml. This can be used to prompt an AI to generate a new tool. Example prompt for Cursor Agent:

create a new tool based on the readme and this openapi doc: https://api.ynab.com/papi/open_api_spec.yaml

The new tool should get the details for a single budget

You can add more tools using the CLI:

# Add a new tool
mcp add tool my-tool

# Example tools you might create:
mcp add tool data-processor
mcp add tool api-client
mcp add tool file-handler

Tool Development

Example tool structure:

import { MCPTool } from "mcp-framework";
import { z } from "zod";

interface MyToolInput {
  message: string;
}

class MyTool extends MCPTool<MyToolInput> {
  name = "my_tool";
  description = "Describes what your tool does";

  schema = {
    message: {
      type: z.string(),
      description: "Description of this input parameter",
    },
  };

  async execute(input: MyToolInput) {
    // Your tool logic here
    return `Processed: ${input.message}`;
  }
}

export default MyTool;

Publishing to npm

  1. Update your package.json:

    • Ensure name is unique and follows npm naming conventions
    • Set appropriate version
    • Add description, author, license, etc.
    • Check bin points to the correct entry file
  2. Build and test locally:

    npm run build
    npm link
    ynab-mcp-server  # Test your CLI locally
    
  3. Login to npm (create account if necessary):

    npm login
    
  4. Publish your package:

    npm publish
    

After publishing, users can add it to their claude desktop client (read below) or run it with npx

Using with Claude Desktop

Local Development

Add this configuration to your Claude Desktop config file:

MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "ynab-mcp-server": {
      "command": "node",
      "args":["/absolute/path/to/ynab-mcp-server/dist/index.js"]
    }
  }
}

After Publishing

Add this configuration to your Claude Desktop config file:

MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "ynab-mcp-server": {
      "command": "npx",
      "args": ["ynab-mcp-server"]
    }
  }
}

Other MCP Clients

Check https://modelcontextprotocol.io/clients for other available clients.

Building and Testing

  1. Make changes to your tools
  2. Run npm run build to compile
  3. The server will automatically load your tools on startup

Learn More

Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
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.
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
ChatWiseThe second fastest AI chatbot™
Tavily Mcp
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
Playwright McpPlaywright MCP server
Serper MCP ServerA Serper MCP Server
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.
DeepChatYour AI Partner on Desktop
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。
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.
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"
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
Amap Maps高德地图官方 MCP Server
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
CursorThe AI Code Editor
WindsurfThe new purpose-built IDE to harness magic
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors