trademe-tinymcp
A simple MCP server for interacting with Trade Me APIs, providing tools for connectivity testing and SDK integration.
README
Trade Me MCP Server
A simple Model Context Protocol (MCP) server for integrating with Trade Me APIs through an external SDK.
Overview
This MCP server provides tools for interacting with Trade Me APIs. It's designed to work with Claude Code and other MCP-compatible applications.
Features
- Hello World: Basic connectivity test
- Server Info: Get information about the MCP server
- SDK Connection Test: Verify connection to Trade Me SDK wrapper
- Extensible: Ready for integration with your Trade Me API SDK
Prerequisites
This MCP server depends on a separate Trade Me SDK project that must be installed alongside it.
Required Project Structure
Both projects should be located in the same parent directory:
parent-folder/
├── trademe-sdk/ # Trade Me SDK project (required dependency)
└── trademe-tinymcp/ # This MCP server project
Installation
-
Ensure you have the Trade Me SDK project:
- Clone the
trademe-sdkproject from: https://github.com/nzduck/trademe-sdk - Place it in the same parent directory as this project
- Clone the
-
Navigate to the project directory:
cd trademe-tinymcp -
Install dependencies using uv (recommended):
uv syncOr using pip:
pip install -e . -
Install the Trade Me SDK dependency:
pip install -e ../trademe-sdk -
Install development dependencies (optional):
uv sync --group dev
Quick Setup Script
For development, you can use the provided script to install both the SDK and MCP server:
bash src/scripts/update-sdk-mcp.sh
This script will:
- Activate the virtual environment
- Install the Trade Me SDK in editable mode from the sibling directory
- Install this MCP server in editable mode
Usage
Running the Server
Run the MCP server using the command-line interface:
python -m trademe_mcp.server
Or using the installed script:
trademe-mcp
Testing the Server
Test that the server is working correctly:
# Test basic functionality
python -c "
import asyncio
from trademe_mcp.server import mcp
async def test():
# This would typically be done by an MCP client
print('Server initialized successfully')
asyncio.run(test())
"
Integration with Claude Code
To use this MCP server with Claude Code, add it to your Claude Code configuration:
{
"mcpServers": {
"trademe": {
"command": "python",
"args": ["-m", "trademe_mcp.server"],
"env": {}
}
}
}
Development
Project Structure
trademe-tinymcp/
├── src/trademe_mcp/
│ ├── __init__.py
│ ├── server.py # Main MCP server implementation
│ └── sdk_wrapper.py # Trade Me SDK wrapper (placeholder)
├── pyproject.toml # Project configuration
├── README.md # This file
└── .gitignore # Git ignore rules
Available Tools
hello_world(): Returns a simple greetingget_server_info(): Returns server metadata and available toolstest_sdk_connection(): Tests the connection to the Trade Me SDK wrapper
Extending the Server
- Replace the SDK wrapper: Update
src/trademe_mcp/sdk_wrapper.pywith your actual Trade Me SDK integration - Add new tools: Create new
@mcp.tool()decorated functions inserver.py - Add resources: Use
@mcp.resource()decorators for data endpoints
Development Tools
Run linting and formatting:
# Format code
uv run black src/
# Lint code
uv run ruff src/
# Run tests
uv run pytest
Troubleshooting
Common Setup Issues
-
"No module named 'trademe_sdk'" error:
- Ensure the
trademe-sdkproject is in the correct location (sibling directory) - If missing, clone it from: https://github.com/nzduck/trademe-sdk
- Install the SDK in editable mode:
pip install -e ../trademe-sdk - Run the update script:
bash src/scripts/update-sdk-mcp.sh
- Ensure the
-
Script fails with path errors:
- Verify the project structure matches the expected layout
- Ensure both projects are in the same parent directory
- Check that the virtual environment is activated
-
Claude Code integration issues:
- Remember to start Claude Code from the virtual environment
- Restart Claude Code after making changes to see updates
Requirements
- Python 3.10 or higher
- MCP SDK 1.2.0 or higher
- Trade Me SDK project (must be in sibling directory)
License
This project is a development stub. Add your license information here.
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。