MCP Hand Detection - 基于 MediaPipe 的手掌检测 MCP 服务
Project description
MCP Hand Detection
一个基于 MediaPipe 的 Model Context Protocol (MCP) 服务器,提供手掌检测功能。
功能特性
- ✅ 基于 MediaPipe 的高精度手掌检测
- ✅ 符合 MCP 标准协议(JSON-RPC 2.0)
- ✅ 支持 stdio 和 HTTP 两种接口
- ✅ 易于集成到支持 MCP 的客户端(如 Cursor、Claude Desktop)
- ✅ 包含预训练模型,开箱即用
安装
pip install mcp-hand-detection
如果需要 HTTP API 功能:
pip install mcp-hand-detection[http]
快速开始
作为 MCP 服务器使用
在 MCP 客户端配置中添加:
{
"mcpServers": {
"hand-detection": {
"command": "mcp-hand-detection"
}
}
}
作为命令行工具使用
# 启动 MCP 服务器(通过 stdio)
mcp-hand-detection
# 启动 HTTP 服务器
mcp-hand-detection-http --port 8080
作为 Python 库使用
from mcp_hand_detection import MCPServer
# 创建服务器实例
server = MCPServer()
# 检测手掌
result = server._detect_hand("/path/to/image.jpg")
print(result)
HTTP API 使用示例
from mcp_hand_detection import create_app
app = create_app()
app.run(host='0.0.0.0', port=8080)
或者使用命令行:
mcp-hand-detection-http --host 0.0.0.0 --port 8080
然后通过 HTTP 调用:
# 文件上传
curl -X POST http://localhost:8080/api/detect -F "image=@hand.jpg"
# Base64 编码
curl -X POST http://localhost:8080/api/detect \
-H "Content-Type: application/json" \
-d '{"image_base64": "...", "image_format": "jpg"}'
API 文档
MCP 工具
- 工具名称:
detect_hand - 描述: 检测图片中是否存在手掌
- 参数:
image_path(string, 必需): 图片文件路径
- 返回: JSON 格式的检测结果
HTTP API
GET /health- 健康检查GET /api/tools- 获取工具列表POST /api/detect- 检测手掌- 支持文件上传 (
multipart/form-data) - 支持 Base64 编码 (
application/json)
- 支持文件上传 (
系统要求
- Python 3.9+
- OpenCV
- MediaPipe 0.10+
- NumPy
许可证
MIT License
贡献
欢迎提交 Issue 和 Pull Request!
链接
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file mcp_hand_detection-1.0.1.tar.gz.
File metadata
- Download URL: mcp_hand_detection-1.0.1.tar.gz
- Upload date:
- Size: 5.8 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e7457ae18f36874213437fe52854ee9c5688577c04634f3f7a2b29fa50113f73
|
|
| MD5 |
5f1082082d84095278cda805225902e3
|
|
| BLAKE2b-256 |
59a333bc945e3615b7ae39ea1044e839ba19b7fb2b56cb1c6f9285a0c9663bfe
|
File details
Details for the file mcp_hand_detection-1.0.1-py3-none-any.whl.
File metadata
- Download URL: mcp_hand_detection-1.0.1-py3-none-any.whl
- Upload date:
- Size: 5.9 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fb464e00e100e4240a01684079e071ff13dacac02fbf47b7a3bfd6ca834788e4
|
|
| MD5 |
34e1fae2bb03ce9ae62471e569cd4e7e
|
|
| BLAKE2b-256 |
cf93f35fcb4c3d17e139ee41c28a346f18fe478dd42e90f77a9f8f9da64271b4
|