{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_tqtf7eytw4zu","handle":"undoom-sketch-mcp","url":"https://wellknown.network/agents/undoom-sketch-mcp","links":{"self":"https://wellknown.network/agents/undoom-sketch-mcp/record.json","html":"https://wellknown.network/agents/undoom-sketch-mcp","markdown":"https://wellknown.network/agents/undoom-sketch-mcp/record.md","api":"https://wellknown.network/api/v1/agents/undoom-sketch-mcp","status":"https://wellknown.network/api/v1/agents/undoom-sketch-mcp/status","claim":"https://wellknown.network/agents/undoom-sketch-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/undoom-sketch-mcp/claim.json","badge":"https://wellknown.network/agents/undoom-sketch-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/undoom-sketch-mcp/history","tools":"https://wellknown.network/api/v1/agents/undoom-sketch-mcp/tools"},"ard":{"identifier":"urn:air::server:undoom-sketch-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"undoom-sketch-mcp","summary":"A MCP server for converting images to sketch effects with multiple styles and batch processing capabilities","description":"# MCP 图片素描转换器\n\n一个基于 MCP (Model Context Protocol) 的图片素描化服务器，可以将普通图片转换为素描效果。\n\n## 功能特性\n\n- 🎨 **多种素描风格**：支持经典、详细、柔和三种不同的素描风格\n- 📁 **批量处理**：支持批量转换文件夹中的所有图片\n- 🖼️ **多格式支持**：支持 JPG、PNG、BMP、GIF、TIFF、WEBP 等常见图片格式\n- 🌏 **中文路径支持**：完美支持中文文件名和路径\n- ⚙️ **参数可调**：可自定义模糊程度和对比度参数\n- 📊 **图片信息查看**：提供图片基本信息和推荐参数\n\n## 安装要求\n\n- Python >= 3.13\n- 依赖包：\n  - mcp[cli] >= 1.12.3\n  - opencv-python >= 4.8.0\n  - numpy >= 1.24.0\n\n## 安装方法\n\n1. 克隆项目：\n```bash\ngit clone <repository-url>\ncd mcp-test\n```\n\n2. 安装依赖：\n```bash\npip install -e .\n```\n\n或使用 uv：\n```bash\nuv sync\n```\n\n## 使用方法\n\n### 启动服务器\n\n```bash\npython main.py\n```\n\n### 可用工具\n\n#### 1. 单张图片转换\n```python\nconvert_image_to_sketch(\n    image_path=\"/path/to/image.jpg\",\n    blur_size=21,\n    contrast=256.0,\n    style=\"classic\"\n)\n```\n\n#### 2. 批量图片转换\n```python\nbatch_convert_images(\n    folder_path=\"/path/to/folder\",\n    blur_size=21,\n    contrast=256.0,\n    style=\"detailed\"\n)\n```\n\n#### 3. 获取图片信息\n```python\nget_image_info(image_path=\"/path/to/image.jpg\")\n```\n\n### 素描风格说明\n\n- **classic**：经典素描风格，平衡的线条和对比度\n- **detailed**：详细素描风格，更清晰的线条和细节\n- **soft**：柔和素描风格，更柔和的效果，适合风景图\n\n### 参数说明\n\n- `image_path`：图片文件的完整路径（必需）\n- `blur_size`：高斯模糊核大小（3-101，必须为奇数，默认21）\n- `contrast`：对比度参数（50-500，默认256.0）\n- `style`：素描风格（classic/detailed/soft，默认classic）\n\n### 参数建议\n\n- **大图片**（>200万像素）：blur_size=31-51，contrast=200-300\n- **中等图片**（50万-200万像素）：blur_size=21-31，contrast=256\n- **小图片**（<50万像素）：blur_size=11-21，contrast=300-400\n\n## 输出文件\n\n转换后的素描图片会保存在原图片相同目录下，文件名格式为：\n```\nSketch_{style}_{原文件名}.jpg\n```\n\n例如：`Sketch_classic_photo.jpg`\n\n## 支持的图片格式\n\n- JPG / JPEG\n- PNG\n- BMP\n- GIF\n- TIFF\n- WEBP\n\n## 技术实现\n\n本项目使用以下技术：\n\n- **OpenCV**：图像处理和计算机视觉\n- **NumPy**：数值计算\n- **MCP (Model Context Protocol)**：与AI模型的通信协议\n- **FastMCP**：快速MCP服务器实现\n\n## 核心算法\n\n素描效果通过以下步骤实现：\n1. 将彩色图片转换为灰度图\n2. 创建反转的灰度图\n3. 对反转图像应用高斯模糊\n4. 使用颜色减淡混合模式生成素描效果\n5. 根据风格进行后处理优化\n\n## 注意事项\n\n- 确保图片文件存在且可读\n- 处理大图片时可能需要较长时间\n- 建议在处理前备份原图片\n- 支持中文路径和文件名\n\n## 许可证\n\n本项目采用开源许可证，具体请查看 LICENSE 文件。\n\n## 贡献\n\n欢迎提交 Issue 和 Pull Request 来改进这个项目！","publisher":null,"homepage":"https://github.com/undoom/undoom-sketch-mcp","repository":"https://github.com/undoom/undoom-sketch-mcp","version":"0.1.4","license":"MIT","protocols":["mcp"],"tags":["ai","computer-vision","image-processing","mcp","opencv","sketch"],"pricing":null,"endpoints":[{"url":"pypi:undoom-sketch-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"dev.version-control","name":"Version Control","confidence":1,"provenance":"derived"},{"slug":"media.image-understanding","name":"Image Understanding","confidence":0.638,"provenance":"derived"}],"categories":["dev","media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"undoom-sketch-mcp","registry":"pypi","observedAt":"2026-10-22T22:25:04.619Z","publishedAt":"2025-08-07T15:53:15.299288Z","latestVersion":"0.1.4"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"undoom-sketch-mcp","url":"https://pypi.org/project/undoom-sketch-mcp/","firstSeenAt":"2026-09-10T14:23:52.852Z","fetchedAt":"2026-10-22T22:24:02.212Z","normalizedAt":"2026-10-22T22:24:02.212Z"}]},"firstSeenAt":"2026-09-10T14:23:52.852Z","updatedAt":"2026-10-22T22:25:04.619Z"}