{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_zxydut3cw2fj","handle":"mcp-idcard-photo","url":"https://wellknown.network/agents/mcp-idcard-photo","links":{"self":"https://wellknown.network/agents/mcp-idcard-photo/record.json","html":"https://wellknown.network/agents/mcp-idcard-photo","markdown":"https://wellknown.network/agents/mcp-idcard-photo/record.md","api":"https://wellknown.network/api/v1/agents/mcp-idcard-photo","status":"https://wellknown.network/api/v1/agents/mcp-idcard-photo/status","claim":"https://wellknown.network/agents/mcp-idcard-photo/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-idcard-photo/claim.json","badge":"https://wellknown.network/agents/mcp-idcard-photo/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-idcard-photo/history","tools":"https://wellknown.network/api/v1/agents/mcp-idcard-photo/tools"},"ard":{"identifier":"urn:air::server:mcp-idcard-photo","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-idcard-photo","summary":"MCP服务器：证件照生成工具，提供AI证件照生成功能","description":"# 生成证件照 MCP 服务器\n\n基于阿里云视觉智能开放平台（VIAPI）高清人体分割（SegmentHDBody）与人脸关键点检测（DetectFace），提供一个工具即可一键生成并裁剪标准证件照，支持白/蓝/红背景与常用尺寸（一寸、二寸）。\n\n## ✨ 核心特性\n\n- 🎯 单一工具：`make_id_photo` 完成生成 → 裁剪 → 保存全流程\n- 🖼️ 背景替换：支持 `white` / `blue` / `red` 三种背景\n - 📐 规格支持：一寸（295×413）、二寸-标准（413×531）、二寸-大（413×579）\n- 💾 自动保存：默认保存到桌面；可指定目录或文件路径\n- ⚡ 同步返回：直接返回云端图片地址与本地保存路径，无需任务查询\n\n## 🔑 配置阿里云 AccessKey\n\n建议使用 RAM 用户的 AccessKey，并为其分配合适权限（如仅 `viapi-imageseg:*`）。请在运行环境设置以下环境变量（任一组即可）：\n\n```bash\nexport ALI_ACCESS_KEY_ID=\"你的AccessKeyId\"\nexport ALI_ACCESS_KEY_SECRET=\"你的AccessKeySecret\"\n```\n\n或使用通用变量名：\n\n```bash\nexport ALIBABA_CLOUD_ACCESS_KEY_ID=\"你的AccessKeyId\"\nexport ALIBABA_CLOUD_ACCESS_KEY_SECRET=\"你的AccessKeySecret\"\n```\n\nWindows PowerShell：\n\n```powershell\n$env:ALI_ACCESS_KEY_ID = \"你的AccessKeyId\"\n$env:ALI_ACCESS_KEY_SECRET = \"你的AccessKeySecret\"\n$env:ALI_REGION = \"cn-shanghai\" # 可选\n```\n\n## 🚀 启动服务\n\n直接运行模块：\n\n```bash\npython -m mcp_idcard_photo.server\n```\n\n## 🔧 在 MCP 客户端中配置\n\n以 Claude Desktop / Cline / Kiro 为例：\n\n```json\n{\n  \"mcpServers\": {\n    \"id-photo\": {\n      \"command\": \"python\",\n    \"args\": [\"-m\", \"mcp_idcard_photo.server\"],\n    \"env\": {\n        \"ALI_ACCESS_KEY_ID\": \"ak-xxxx\",\n        \"ALI_ACCESS_KEY_SECRET\": \"sk-xxxx\"\n      },\n      \"disabled\": false,\n      \"autoApprove\": []\n    }\n  }\n}\n```\n\n## 📖 使用指南\n\n### 工具：`make_id_photo`\n\n生成并保存标准证件照（同步）。流程：\n1) 使用 `image_url + bg` 调用阿里云高清人体分割，得到透明前景人像；\n2) 调用人脸关键点检测进行对齐与构图，按目标尺寸裁剪：默认二寸-标准（413×531），若传入 `spec` 则按规格；\n3) 合成到指定背景色并保存到桌面或 `output_path` 指定位置；返回保存路径与元数据。\n\n#### 参数\n\n| 参数 | 类型 | 必填 | 默认值 | 说明 |\n|------|------|------|--------|------|\n| `image_url` | string | ✅ | - | 输入图片地址，需公网可访问的 `http/https` 链接 |\n| `output_path` | string | ❌ | 桌面 | 输出目录或最终文件路径；为目录时自动命名文件 |\n| `bg` | enum | ❌ | `blue` | 背景色：`white`、`blue`、`red` |\n| `spec` | enum | ❌ | - | 证件照规格：`一寸`、`二寸-标准`、`二寸-大` |\n\n裁剪默认比例（推荐）：\n- 头顶到画面上边距约 `12%`（`top_margin_ratio = 0.12`）\n- 垂直裁剪高度约为主体包围盒的 `92%`（`expand_ratio = 0.92`）\n\n#### 调用示例\n\n- 使用默认蓝底与默认二寸标准尺寸并保存到桌面：\n\n```\nmake_id_photo(image_url=\"https://example.com/portrait.jpg\")\n```\n\n…","publisher":null,"homepage":"https://github.com/fengjinchao/mcp-image-super-resolution#readme","repository":"https://github.com/fengjinchao/mcp-image-super-resolution#readme","version":"1.0.4","license":"MIT","protocols":["mcp"],"tags":["ai","aliyun","image","image-enhancement","mcp","super-resolution","upscale"],"pricing":null,"endpoints":[{"url":"pypi:mcp-idcard-photo","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":"media.image-editing","name":"Image Editing","confidence":1,"provenance":"declared"}],"categories":["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":"mcp-idcard-photo","registry":"pypi","observedAt":"2026-10-22T09:23:41.284Z","publishedAt":"2026-04-25T04:01:14.643112Z","latestVersion":"1.0.4"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-idcard-photo","url":"https://pypi.org/project/mcp-idcard-photo/","firstSeenAt":"2026-09-10T02:22:49.570Z","fetchedAt":"2026-10-22T09:22:20.616Z","normalizedAt":"2026-10-22T09:22:20.616Z"}]},"firstSeenAt":"2026-09-10T02:22:49.570Z","updatedAt":"2026-10-22T09:23:41.284Z"}