{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_j8v8mtmjf8tr","handle":"mcp-imgutils","url":"https://wellknown.network/agents/mcp-imgutils","links":{"self":"https://wellknown.network/agents/mcp-imgutils/record.json","html":"https://wellknown.network/agents/mcp-imgutils","markdown":"https://wellknown.network/agents/mcp-imgutils/record.md","api":"https://wellknown.network/api/v1/agents/mcp-imgutils","status":"https://wellknown.network/api/v1/agents/mcp-imgutils/status","claim":"https://wellknown.network/agents/mcp-imgutils/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-imgutils/claim.json","badge":"https://wellknown.network/agents/mcp-imgutils/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-imgutils/history","tools":"https://wellknown.network/api/v1/agents/mcp-imgutils/tools"},"ard":{"identifier":"urn:air::server:mcp-imgutils","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-imgutils","summary":"MCP服务：将本地图片和网络图片发送给LLM","description":"# MCP图片工具服务\n\n这是一个基于Model Context Protocol (MCP)的全方位图片工具服务，提供图片分析和AI图片生成功能。\n\n## 功能特性\n\n### 📊 图片分析功能\n- **🖼️ 图片查看与分析**: 将本地图片和网络图片转换为LLM可分析的格式\n- **🌐 URL图片支持**: 直接支持HTTP/HTTPS图片URL，无需下载到本地\n- **📊 完整图片信息**: 获取分辨率、大小、格式、颜色模式等技术参数\n- **📷 EXIF元数据提取**: 提取拍摄参数、设备信息、GPS数据等完整EXIF信息\n- **🔄 智能格式处理**: 自动处理各种图片格式和大小调整\n- **🔒 安全验证**: URL格式验证、Content-Type检查、超时控制\n- **🧹 自动清理**: 临时文件自动管理，无磁盘泄漏\n- **📝 专业术语支持**: 保持英文EXIF键名，便于LLM理解专业摄影术语\n\n### 🎨 AI图片生成功能\n- **🚀 多模型支持**: 支持 BFL FLUX 和 OpenAI DALL-E 系列模型\n  - **BFL FLUX**: flux-pro-1.1, flux-pro-1.1-ultra, flux-pro, flux-dev\n  - **OpenAI DALL-E**: dall-e-3, dall-e-2\n- **📐 智能尺寸**: 预设尺寸和自定义尺寸，自动调整到最佳参数\n- **⚡ 高质量生成**: 业界领先的文本生成图片质量\n- **📁 本地保存**: 图片自动下载到本地目录，避免大文件传输问题\n- **🛡️ 完整错误处理**: API限制、网络错误、参数验证等全面处理\n- **🔄 智能工作流**: 生成后可直接使用view_image工具查看分析\n- **🎯 灵活配置**: 支持临时路径覆盖，满足不同使用场景\n\n## 安装\n\n确保已安装必要的依赖：\n\n```bash\nuv install\n# 或者\npip install -e .\n```\n\n## 使用方法\n\n### Claude Desktop配置\n\n这是一个MCP服务器，需要通过Claude Desktop配置使用。\n\n**配置文件位置**:\n\n- **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`\n- **Windows**: `%APPDATA%\\Claude\\claude_desktop_config.json`\n\n**配置内容**:\n\n在Claude Desktop的配置文件中添加以下配置：\n\n```json\n{\n  \"mcpServers\": {\n    \"mcp-imgutils\": {\n      \"command\": \"uvx\",\n      \"args\": [\"mcp-imgutils\"],\n      \"env\": {\n        \"BFL_API_KEY\": \"your-bfl-api-key-here\",\n        \"OPENAI_API_KEY\": \"your-openai-api-key-here\"\n      }\n    }\n  }\n}\n```\n\n### 🔑 API密钥配置\n\n#### BFL (Black Forest Labs) API密钥\n\n要使用 BFL FLUX 模型生成图片，需要配置 BFL API密钥：\n\n1. **获取API密钥**: 访问 [BFL API Portal](https://api.bfl.ai/) 注册并获取API密钥\n2. **配置方式**:\n   - **方式1 (推荐)**: 在Claude Desktop配置中添加环境变量（如上所示）\n   - **方式2**: 设置系统环境变量 `export BFL_API_KEY=your-api-key`\n\n#### OpenAI API密钥\n\n要使用 OpenAI DALL-E 模型生成图片，需要配置 OpenAI API密钥：\n\n1. **获取API密钥**: 访问 [OpenAI API Portal](https://platform.openai.com/api-keys) 注册并获取API密钥\n2. **配置方式**:\n   - **方式1 (推荐)**: 在Claude Desktop配置中添加环境变量（如上所示）\n   - **方式2**: 设置系统环境变量 `export OPENAI_API_KEY=your-api-key`\n\n#### 图片保存目录配置（可选）\n\n默认情况下，生成的图片保存到：\n\n**BFL FLUX 模型**:\n-…","publisher":null,"homepage":null,"repository":null,"version":"5.2.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:mcp-imgutils","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"media.image-generation","name":"Image Generation","confidence":0.756,"provenance":"derived"}],"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-imgutils","registry":"pypi","observedAt":"2026-11-03T13:26:52.137Z","publishedAt":"2025-08-10T18:41:04.787816Z","latestVersion":"5.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-imgutils","url":"https://pypi.org/project/mcp-imgutils/","firstSeenAt":"2026-09-10T02:22:52.705Z","fetchedAt":"2026-11-03T13:26:22.935Z","normalizedAt":"2026-11-03T13:26:22.935Z"}]},"firstSeenAt":"2026-09-10T02:22:52.705Z","updatedAt":"2026-11-03T13:26:52.137Z"}