- Toshl MCP Server
Content
Toshl MCP Server
An MCP (Model Context Protocol) server for integrating Toshl Finance with AI agents.
Overview
The Toshl MCP Server provides a bridge between AI agents and the Toshl Finance API. It allows AI agents to access financial data from Toshl, analyze it, and provide insights and advice based on the data.
Features
-
READ access to Toshl Finance API endpoints:
- Accounts
- Categories
- Tags
- Budgets
- User information
- Planning
-
MCP Resources:
- List accounts
- Get account details
- List categories
- Get category details
- List tags
- Get tag details
- List budgets
- Get budget details
- Get budget history
- Get user profile
- Get account summary
- List entries
-
MCP Tools:
- Account tools (list accounts, get account details)
- Category tools (list categories, get category details)
- Tag tools (list tags, get tag details)
- Budget tools (list budgets, get budget details, get budget history)
- User tools (get profile, get summary, get payment types, get payments)
- Entry tools (list entries, get entry details, get entry sums, get entry timeline, create entry, update entry, delete entry, manage entries)
- Analysis tools (analyze spending by category, analyze budget performance, analyze account balances)
Prerequisites
- Node.js (v18.x or higher)
- npm (v8.x or higher)
- Toshl Finance API token
Get API Token
- go to https://developer.toshl.com/apps/
- create new personal token. Insert name for token under "Description" and your account password under "Password"
Installation
- Clone the repository:
git clone https://github.com/yourusername/toshl-mcp-server.git
cd toshl-mcp-server
- Install dependencies:
npm install
- Create a
.envfile based on the.env.examplefile:
cp .env.example .env
- Edit the
.envfile and add your Toshl API token:
TOSHL_API_TOKEN=your_api_token
Building
Build the project:
npm run build
Running
Start the server:
npm start
Configure MCP server
"toshl-mcp-server": {
"command": "node",
"args": [
"/root/source/personal/toshl-mcp-server/dist/index.js"
],
"env": {
"TOSHL_API_TOKEN": "your-token",
"TOSHL_API_BASE_URL": "https://api.toshl.com",
"MCP_SERVER_NAME": "toshl-mcp-server",
"MCP_SERVER_VERSION": "0.1.0",
"CACHE_TTL": "3600",
"CACHE_ENABLED": "true",
"LOG_LEVEL": "debug"
},
"disabled": false,
"autoApprove": []
}
Development
Run the server in development mode:
npm run dev
Documentation
Project Structure
toshl-mcp-server/
├── src/
│ ├── index.ts # Entry point
│ ├── server/ # MCP server implementation
│ │ └── server.ts # Main server class
│ ├── api/ # Toshl API client
│ │ ├── toshl-client.ts # Base API client
│ │ ├── auth.ts # Authentication module
│ │ └── endpoints/ # Endpoint-specific clients
│ │ ├── accounts.ts # Accounts API client
│ │ ├── categories.ts # Categories API client
│ │ ├── tags.ts # Tags API client
│ │ ├── budgets.ts # Budgets API client
│ │ ├── entries.ts # Entries API client
│ │ ├── me.ts # User API client
│ │ └── planning.ts # Planning API client
│ ├── resources/ # MCP resource handlers
│ │ ├── account-resources.ts # Account resources
│ │ ├── category-resources.ts# Category resources
│ │ ├── tag-resources.ts # Tag resources
│ │ ├── budget-resources.ts # Budget resources
│ │ └── user-resources.ts # User resources
│ ├── tools/ # MCP tool handlers
│ │ ├── account-tools.ts # Account tools
│ │ ├── category-tools.ts # Category tools
│ │ ├── tag-tools.ts # Tag tools
│ │ ├── budget-tools.ts # Budget tools
│ │ ├── user-tools.ts # User tools
│ │ └── analysis-tools.ts # Financial analysis tools
│ └── utils/ # Utility functions
│ ├── cache.ts # Caching utilities
│ ├── error-handler.ts # Error handling utilities
│ ├── logger.ts # Logging utilities
│ └── types.ts # TypeScript type definitions
├── dist/ # Compiled JavaScript files
├── .env # Environment variables
├── .env.example # Example environment variables
├── package.json # Project dependencies
├── tsconfig.json # TypeScript configuration
└── README.md # Project documentation
Configuration
The server can be configured using environment variables:
TOSHL_API_TOKEN: Your Toshl API tokenTOSHL_API_BASE_URL: The base URL for the Toshl API (default: https://api.toshl.com)MCP_SERVER_NAME: The name of the MCP server (default: toshl-mcp-server)MCP_SERVER_VERSION: The version of the MCP server (default: 0.1.0)CACHE_TTL: Time to live for cached data in seconds (default: 3600)CACHE_ENABLED: Whether caching is enabled (default: true)LOG_LEVEL: Logging level (default: info)
License
MIT
Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
DeepChatYour AI Partner on Desktop
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
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.
Playwright McpPlaywright MCP server
WindsurfThe new purpose-built IDE to harness magic
CursorThe AI Code Editor
Tavily Mcp
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
ChatWiseThe second fastest AI chatbot™
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
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.
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
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。
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"
Serper MCP ServerA Serper MCP Server
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