Django DRF MCP Server

Django DRF MCP Server

Enables natural language interaction with Django REST Framework APIs by auto-discovering ViewSets and providing CRUD tools, requiring minimal setup.

Category
访问服务器

README

Django REST Framework + MCP Integration

A simple Django REST Framework application with integrated Model Context Protocol (MCP) server.

Overview

This project demonstrates the simplest way to add MCP (Model Context Protocol) support to any Django REST Framework project. Just copy one file (mcp_view.py) and add one URL pattern - that's it!

Features

  • Django REST Framework API - Complete CRUD operations for User management
  • Simple MCP Integration - Single file MCP view with auto-discovery
  • Zero Dependencies - Only uses Django, DRF, and Python standard library
  • Auto-discovery - Automatically finds DRF ViewSets and creates MCP tools

Quick Start

1. Install Dependencies

pip install -r requirements.txt

2. Setup Database

python manage.py migrate

3. Start the Server

python manage.py runserver

The server provides:

  • REST API: http://localhost:8000/api/users/
  • MCP Endpoint: http://localhost:8000/mcp/
  • Admin: http://localhost:8000/admin/

Adding MCP to Your Django Project

Want to add MCP support to your existing Django DRF project? It's incredibly simple:

1. Copy the MCP View

Copy django_mcp_project/mcp_view.py to your Django project.

2. Add URL Pattern

In your urls.py:

from your_project.mcp_view import MCPView

urlpatterns = [
    # your existing patterns...
    path("mcp/", MCPView.as_view(), name="mcp"),
]

3. That's it!

Your Django project now has MCP support. The view automatically discovers all your DRF ViewSets and creates MCP tools for them.

Testing MCP Integration

Test that your MCP endpoint is working:

curl -X POST http://127.0.0.1:8000/mcp/ \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {}}'

API Endpoints

User Management

  • GET/POST /api/users/ - List all users / Create new user
  • GET/PUT/PATCH/DELETE /api/users/{id}/ - User detail operations
  • POST /api/users/{id}/activate/ - Activate user
  • POST /api/users/{id}/deactivate/ - Deactivate user

MCP Integration

  • POST /mcp/ - MCP JSON-RPC endpoint with auto-discovered tools

Project Structure

django-drf-mcp/
├── django_mcp_project/
│   ├── mcp_view.py          # 🌟 The magic file - copy this to any DRF project
│   ├── settings.py          # Django settings
│   ├── urls.py              # URL configuration with MCP endpoint
│   └── wsgi.py              # WSGI configuration
├── users/                   # Example Django app with User model
│   ├── models.py            # Extended User model
│   ├── serializers.py       # DRF serializers
│   ├── views.py             # DRF ViewSets
│   └── urls.py              # User API endpoints
├── manage.py                # Django management script
├── requirements.txt         # Dependencies
└── .vscode/                 # VS Code MCP client configuration

How It Works

The MCPView class in mcp_view.py:

  1. Auto-discovers all Django apps and their ViewSets
  2. Creates MCP tools for each CRUD operation (list, create, retrieve, update, destroy)
  3. Provides JSON-RPC interface compatible with MCP clients
  4. Requires zero configuration - just works out of the box

VS Code Integration

Add to your .vscode/mcp.json:

{
  "servers": {
    "django-mcp": {
      "type": "http",
      "url": "http://127.0.0.1:8000/mcp/"
    }
  }
}

License

MIT License - feel free to use this in your projects!

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
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
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
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
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
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
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
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