Job Finder MCP Server
Enables users to search for remote job listings using Playwright browser automation, fully containerized with Docker and compatible with Claude Desktop.
README
Job Finder MCP Server
A Model Context Protocol (MCP) server built with Python that allows Claude Desktop to search for remote job listings using Playwright browser automation. The project is fully containerized with Docker for easy deployment and portability.
Features
- Search remote jobs using Playwright
- MCP server compatible with Claude Desktop
- Dockerized for easy deployment
- Uses Groq API for intelligent processing
- Supports environment variables for secure API key management
Tech Stack
- Python 3.12
- Model Context Protocol (MCP)
- Playwright
- Docker
- Claude Desktop
- Groq API
Project Structure
Job_Finder_mcp_docker/
│
├── mcp_job.py # MCP server implementation
├── Dockerfile # Docker configuration
├── requirements.txt # Python dependencies
├── .gitignore
└── README.md
Installation
1. Clone the repository
git clone https://github.com/Zakria774/Job_Finder_mcp_docker.git
cd Job_Finder_mcp_docker
2. Create a virtual environment
python3 -m venv .venv
source .venv/bin/activate
3. Install dependencies
pip install -r requirements.txt
playwright install chromium
4. Create a .env file
Create a file named .env
GROQ_API_KEY=your_groq_api_key
Do not upload your
.envfile to GitHub.
Running Locally
Start the MCP server:
python mcp_job.py
The server will wait for requests from an MCP client such as Claude Desktop.
Running with Docker
Build the Docker image:
docker build -t job_finder .
Run the Docker container:
docker run -i --rm job_finder
Claude Desktop Configuration
Add the following configuration to your claude_desktop_config.json:
{
"mcpServers": {
"job_finder": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"job_finder"
]
}
}
}
Restart Claude Desktop after saving the configuration.
Example Prompt
Find me remote Python jobs using my job finder tool.
Claude Desktop will invoke the MCP server and return job listings.
Environment Variables
| Variable | Description |
|---|---|
| GROQ_API_KEY | Your Groq API key |
Security
Ensure your .gitignore includes:
.env
.venv/
__pycache__/
*.pyc
Never commit API keys or secrets to GitHub.
Author
Muhammad Zakria
GitHub: https://github.com/Zakria774
License
This project is open source and available under the MIT License.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。