truqu-mcp

truqu-mcp

Enables querying and managing Truqu goals, feedback, and reflections by loading exported JSON data and providing tools to filter and retrieve them.

Category
访问服务器

README

Truqu MCP Server

A Model Context Protocol (MCP) server for interacting with Truqu goal and feedback data, built with TypeScript.

Getting Started

Step 1: Export your Truqu data

  1. In Truqu, click on your profile picture (top right corner)
  2. Select Settings
  3. Click on Your data
  4. Download your data as a JSON file

Step 2: Add MCP server to your client

For Claude Desktop:

  1. Open Claude Desktop settings
  2. Go to the "Developer" section
  3. Click "Edit Config" button under "Local MCP servers"
  4. Edit the config file to add the MCP server:
{
  "mcpServers": {
    "truqu-mcp": {
      "command": "npx",
      "args": ["truqu-mcp", "/path/to/your/downloaded-truqu-data.json"]
    }
  }
}
  1. Replace /path/to/your/downloaded-truqu-data.json with the actual path to your Truqu JSON file
  2. Restart Claude Desktop

For other MCP clients:

Run the server directly:

npx truqu-mcp "/path/to/your/downloaded-truqu-data.json"

That's it! The server will start and load your Truqu data automatically.

What is MCP?

The Model Context Protocol (MCP) is an open standard that enables AI applications to securely connect to external data sources and tools. This server provides a foundation for building custom MCP integrations.

Features

  • Built with TypeScript for type safety
  • Uses the official MCP TypeScript SDK
  • Load and parse Truqu JSON data exports
  • Filter data by user ownership automatically
  • Date range filtering for goals, feedback, and reflections
  • Comprehensive goal management tools
  • Hot reload during development
  • Production-ready build configuration

Prerequisites

  • Node.js 18 or higher
  • npm or yarn

Installation

Option 1: Use directly with npx (Recommended)

No installation required! Just use the published npm package:

npx truqu-mcp "/path/to/your/truqu-data.json"

Option 2: Local development

  1. Clone this repository
  2. Install dependencies:
npm install

Configuration

The server requires a path to your Truqu data JSON file. You can provide this in two ways:

Method 1: Command Line Argument (Recommended)

# Using npm package (recommended)
npx truqu-mcp "/path/to/your/truqu-data.json"

# Local development (alternative)
tsx src/index.ts "/path/to/your/truqu-data.json"

Method 2: Environment Variable

# Using npm package (recommended)
export TRUQU_DATA_PATH="/path/to/your/truqu-data.json"
npx truqu-mcp

# Local development (alternative)
export TRUQU_DATA_PATH="/path/to/your/truqu-data.json"
tsx src/index.ts

Development (Local only)

For local development and contributions:

Start the development server with hot reload:

tsx src/index.ts "/path/to/your/truqu-data.json"

Watch for changes during development:

npm run watch

Building (Local only)

Build the TypeScript code to JavaScript:

npm run build

Project Structure

truqu-mcp/
├── src/
│   └── index.ts          # Main server implementation
├── dist/                 # Built JavaScript files (after npm run build)
├── package.json          # Project configuration and dependencies
├── tsconfig.json         # TypeScript configuration
├── .gitignore           # Git ignore rules
└── README.md            # This file

Available Tools

The server provides tools to interact with Truqu goal and feedback data:

Goals

  • get_goals_list: Get a list of user's goals with basic information (id, title, dates, status)
    • Parameters: startDate (optional string), endDate (optional string) - Date filtering in YYYY-MM-DD format
  • get_goals_detailed: Get detailed information about user's goals including action points and items
    • Parameters: startDate (optional string), endDate (optional string) - Date filtering in YYYY-MM-DD format
  • get_goal_by_id: Get a specific goal by its ID
    • Parameters: goalId (required string) - The ID of the goal to retrieve

Feedback

  • get_feedback: Get feedback/reviews given to the user
    • Parameters: startDate (optional string), endDate (optional string) - Date filtering in YYYY-MM-DD format

Reflections

  • get_reflections: Get user's reflection reports
    • Parameters: startDate (optional string), endDate (optional string) - Date filtering in YYYY-MM-DD format

Usage Example

Once the server is running with your Truqu data configured, you can use these tools:

  1. Get a list of your goals:
// Get all goals
get_goals_list({});

// Get goals from 2024
get_goals_list({ startDate: "2024-01-01", endDate: "2024-12-31" });
  1. Get detailed goal information:
// Get detailed info for all goals
get_goals_detailed({});

// Get a specific goal
get_goal_by_id({ goalId: "168a7025-f6cc-41cc-abd7-087467c634ae" });
  1. Get feedback and reflections:
// Get all feedback
get_feedback({});

// Get reflections from 2025
get_reflections({ startDate: "2025-01-01" });

Data Filtering

  • The server automatically filters data to show only items owned by the current user
  • Goals are filtered by the owner.id field
  • Reviews are filtered by the professional.id field
  • Reflections are filtered by the user.id field
  • Date filtering uses the created field for goals and reflections, and the date field for reviews

Extending the Server

To add new tools:

  1. Add the tool definition in the ListToolsRequestSchema handler
  2. Implement the tool logic in the CallToolRequestSchema handler
  3. Update this README with documentation for your new tools

MCP Client Configuration

To use this server with an MCP client, you have several options:

Option 1: Using npm package (Recommended)

Run the server directly from npm:

npx truqu-mcp "/path/to/your/truqu-data.json"

Option 2: Local development

For local development and testing:

npx tsx src/index.ts "/path/to/your/truqu-data.json"

Client Configuration

Configure your MCP client with one of these approaches:

Using npm package (Recommended):

  • Command: npx truqu-mcp "/path/to/your/truqu-data.json"
  • No working directory required

Local development:

  • Command: npx tsx src/index.ts "/path/to/your/truqu-data.json"
  • Working directory: /path/to/truqu-mcp

Example Claude Desktop configuration (npm package):

{
  "mcpServers": {
    "truqu-mcp": {
      "command": "npx",
      "args": ["truqu-mcp", "/path/to/your/truqu-data.json"]
    }
  }
}

Alternative with environment variable:

{
  "mcpServers": {
    "truqu-mcp": {
      "command": "npx",
      "args": ["truqu-mcp"],
      "env": {
        "TRUQU_DATA_PATH": "/path/to/your/truqu-data.json"
      }
    }
  }
}

Local development configuration:

{
  "mcpServers": {
    "truqu-mcp": {
      "command": "npx",
      "args": ["tsx", "src/index.ts", "/path/to/your/truqu-data.json"],
      "cwd": "/path/to/truqu-mcp"
    }
  }
}

Contributing

Contributions are welcome! Please see CONTRIBUTING.md for development setup and guidelines.

Automated Publishing

This package uses GitHub Actions for automated publishing:

  • CI: Runs tests on every push/PR
  • Publish: Automatically publishes to npm when a new tag is created

To release a new version:

  1. Update version: npm version patch (or minor/major)
  2. Push changes: git push origin main --tags
  3. GitHub Actions will automatically build and publish to npm

License

MIT

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选
mcp-server-qdrant

mcp-server-qdrant

这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。

官方
精选
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选