laravel-tasks

laravel-tasks

MCP server that connects to a Laravel Tasks API, enabling AI assistants to perform CRUD operations on tasks.

Category
访问服务器

README

Laravel Tasks API - MCP Server

A Model Context Protocol (MCP) server that connects to your Laravel Tasks API, allowing AI assistants to interact with your task management system.

Features

  • ✅ Health check endpoint
  • ✅ List all tasks
  • ✅ Get task by ID
  • ✅ Create new tasks
  • ✅ Update existing tasks
  • ✅ Delete tasks

Prerequisites

  • Python 3.10 or higher
  • Laravel API running at http://localhost:8000
  • MCP API key from your Laravel application

Installation

  1. Install dependencies:

    pip install -r requirements.txt
    
  2. Set up environment variables:

    cp .env.example .env
    

    Then edit .env and add your MCP_API_KEY.

Configuration

The server uses the following environment variables:

  • API_BASE_URL: Base URL for your Laravel API (default: http://localhost:8000/api/mcp)
  • MCP_API_KEY: Your API key for authentication (required)

Running the Server

For Cursor IDE

Add this to your Cursor settings (.cursor/config.json or Cursor settings):

{
  "mcpServers": {
    "laravel-tasks": {
      "command": "python",
      "args": ["/absolute/path/to/MCP Server/server.py"],
      "env": {
        "MCP_API_KEY": "your-api-key-here",
        "API_BASE_URL": "http://localhost:8000/api/mcp"
      }
    }
  }
}

Testing Locally

You can test the server using the MCP Inspector or by running:

python server.py

Available Tools

The MCP server exposes the following tools:

  1. health_check - Check API health status
  2. list_tasks - Get all tasks
  3. get_task - Get a specific task by ID
  4. create_task - Create a new task (requires title, optional description and status)
  5. update_task - Update an existing task (requires task_id, optional fields to update)
  6. delete_task - Delete a task by ID

API Endpoints

The server connects to these Laravel endpoints:

  • GET /api/mcp/health - Health check
  • GET /api/mcp/tasks - List tasks
  • POST /api/mcp/tasks - Create task
  • GET /api/mcp/tasks/{id} - Get task
  • PUT/PATCH /api/mcp/tasks/{id} - Update task
  • DELETE /api/mcp/tasks/{id} - Delete task

Authentication

All requests include authentication headers:

  • X-AI-Agent-Api-Key: <your MCP_API_KEY>
  • Authorization: Bearer <your MCP_API_KEY>

Project Structure

MCP Server/
├── server.py          # Main entry point - MCP server initialization
├── config.py          # Configuration management class
├── api_client.py      # Laravel API HTTP client class
├── tools.py           # MCP tool definitions and handlers
├── utils.py           # Utility functions
├── requirements.txt   # Python dependencies
├── .env.example      # Environment variables template
└── README.md         # This file

Architecture

The codebase is organized into modular classes:

  • Config (config.py): Manages configuration and environment variables
  • LaravelAPIClient (api_client.py): Handles all HTTP requests to Laravel API
  • TaskTools (tools.py): Defines MCP tools and handles tool execution
  • LaravelTasksMCPServer (server.py): Main server class that ties everything together

Troubleshooting

  • Connection errors: Ensure your Laravel API is running at http://localhost:8000
  • Authentication errors: Verify your MCP_API_KEY is correct
  • Import errors: Make sure all dependencies are installed: pip install -r requirements.txt
  • Module import errors: Ensure you're running from the project root directory

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