chore: duplicate mcp server removal using similarity search

frontend/public/mcp/input/aggregators.json

@@ -2,7 +2,7 @@
   "category": "aggregators",
   "categoryDisplay": "Aggregators",
   "description": "Servers for accessing many apps and tools through a single MCP server.",
-  "totalRepositories": 19,
+  "totalRepositories": 17,
   "repositories": {
     "1mcp--agent": {
       "owner": "1mcp",
@@ -76,30 +76,6 @@
       ],
       "category": "aggregators"
     },
-    "SureScaleAI--openai-gpt-image-mcp": {
-      "owner": "SureScaleAI",
-      "name": "openai-gpt-image-mcp",
-      "url": "https://github.com/SureScaleAI/openai-gpt-image-mcp",
-      "imageUrl": "",
-      "description": "OpenAI GPT image generation/editing MCP server.",
-      "stars": 74,
-      "forks": 23,
-      "license": "MIT License",
-      "language": "TypeScript",
-      "updated_at": "2025-10-03T22:32:34Z",
-      "readme_content": "# openai-gpt-image-mcp\n\n<p align=\"center\">\n  <a href=\"https://www.npmjs.com/package/@modelcontextprotocol/sdk\"><img src=\"https://img.shields.io/npm/v/@modelcontextprotocol/sdk?label=MCP%20SDK&color=blue\" alt=\"MCP SDK\"></a>\n  <a href=\"https://www.npmjs.com/package/openai\"><img src=\"https://img.shields.io/npm/v/openai?label=OpenAI%20SDK&color=blueviolet\" alt=\"OpenAI SDK\"></a>\n  <a href=\"https://github.com/SureScaleAI/openai-gpt-image-mcp/blob/main/LICENSE\"><img src=\"https://img.shields.io/github/license/SureScaleAI/openai-gpt-image-mcp?color=brightgreen\" alt=\"License\"></a>\n  <a href=\"https://github.com/SureScaleAI/openai-gpt-image-mcp/stargazers\"><img src=\"https://img.shields.io/github/stars/SureScaleAI/openai-gpt-image-mcp?style=social\" alt=\"GitHub stars\"></a>\n  <a href=\"https://github.com/SureScaleAI/openai-gpt-image-mcp/actions\"><img src=\"https://img.shields.io/github/actions/workflow/status/SureScaleAI/openai-gpt-image-mcp/main.yml?label=build&logo=github\" alt=\"Build Status\"></a>\n</p>\n\n---\n\nA Model Context Protocol (MCP) tool server for OpenAI's GPT-4o/gpt-image-1 image generation and editing APIs.\n\n- **Generate images** from text prompts using OpenAI's latest models.\n- **Edit images** (inpainting, outpainting, compositing) with advanced prompt control.\n- **Supports**: Claude Desktop, Cursor, VSCode, Windsurf, and any MCP-compatible client.\n\n---\n\n## ✨ Features\n\n- **create-image**: Generate images from a prompt, with advanced options (size, quality, background, etc).\n- **edit-image**: Edit or extend images using a prompt and optional mask, supporting both file paths and base64 input.\n- **File output**: Save generated images directly to disk, or receive as base64.\n\n---\n\n## 🚀 Installation\n\n```sh\ngit clone https://github.com/SureScaleAI/openai-gpt-image-mcp.git\ncd openai-gpt-image-mcp\nyarn install\nyarn build\n```\n\n---\n\n## 🔑 Configuration\n\nAdd to Claude Desktop or VSCode (including Cursor/Windsurf) config:\n\n```json\n{\n  \"mcpServers\": {\n    \"openai-gpt-image-mcp\": {\n      \"command\": \"node\",\n      \"args\": [\"/absolute/path/to/dist/index.js\"],\n      \"env\": { \"OPENAI_API_KEY\": \"sk-...\" }\n    }\n  }\n}\n```\n\nAlso supports Azure deployments:\n\n```json\n{\n  \"mcpServers\": {\n    \"openai-gpt-image-mcp\": {\n      \"command\": \"node\",\n      \"args\": [\"/absolute/path/to/dist/index.js\"],\n      \"env\": { \n        \"AZURE_OPENAI_API_KEY\": \"sk-...\",\n        \"AZURE_OPENAI_ENDPOINT\": \"my.endpoint.com\",\n        \"OPENAI_API_VERSION\": \"2024-12-01-preview\"\n      }\n    }\n  }\n}\n```\n\nAlso supports supplying an environment files:\n\n```json\n{\n  \"mcpServers\": {\n    \"openai-gpt-image-mcp\": {\n      \"command\": \"node\",\n      \"args\": [\"/absolute/path/to/dist/index.js\", \"--env-file\", \"./deployment/.env\"]\n    }\n  }\n}\n```\n\n---\n\n## ⚡ Advanced\n\n- For `create-image`, set `n` to generate up to 10 images at once.\n- For `edit-image`, provide a mask image (file path or base64) to control where edits are applied.\n- Provide an environment file with `--env-file path/to/file/.env`\n- See `src/index.ts` for all options.\n\n---\n\n## 🧑‍💻 Development\n\n- TypeScript source: `src/index.ts`\n- Build: `yarn build`\n- Run: `node dist/index.js`\n\n---\n\n## 📝 License\n\nMIT\n\n---\n\n## 🩺 Troubleshooting\n\n- Make sure your `OPENAI_API_KEY` is valid and has image API access.\n- You must have a [verified OpenAI organization](https://platform.openai.com/account/organization). After verifying, it can take 15–20 minutes for image API access to activate.\n- File paths must be absolute.\n  - **Unix/macOS/Linux**: Starting with `/` (e.g., `/path/to/image.png`)\n  - **Windows**: Drive letter followed by `:` (e.g., `C:/path/to/image.png` or `C:\\path\\to\\image.png`)\n- For file output, ensure the directory is writable.\n- If you see errors about file types, check your image file extensions and formats.\n\n---\n\n## ⚠️ Limitations & Large File Handling\n\n- **1MB Payload Limit:** MCP clients (including Claude Desktop) have a hard 1MB limit for tool responses. Large images (especially high-res or multiple images) can easily exceed this limit if returned as base64.\n- **Auto-Switch to File Output:** If the total image size exceeds 1MB, the tool will automatically save images to disk and return the file path(s) instead of base64. This ensures compatibility and prevents errors like `result exceeds maximum length of 1048576`.\n- **Default File Location:** If you do not specify a `file_output` path, images will be saved to `/tmp` (or the directory set by the `MCP_HF_WORK_DIR` environment variable) with a unique filename.\n- **Environment Variable:**\n  - `MCP_HF_WORK_DIR`: Set this to control where large images and file outputs are saved. Example: `export MCP_HF_WORK_DIR=/your/desired/dir`\n- **Best Practice:** For large or production images, always use file output and ensure your client is configured to handle file paths.\n\n---\n\n## 📚 References\n\n- [OpenAI Images API Documentation](https://platform.openai.com/docs/api-reference/images)\n\n---\n\n## 🙏 Credits\n\n- Built with [@modelcontextprotocol/sdk](https://www.npmjs.com/package/@modelcontextprotocol/sdk)\n- Uses [openai](https://www.npmjs.com/package/openai) Node.js SDK \n- Built by [SureScale.ai](https://surescale.ai)\n- Contributions from [Axle Research and Technology](https://axleinfo.com/)",
-      "npm_url": "",
-      "npm_downloads": 0,
-      "keywords": [
-        "openai",
-        "mcp",
-        "gpt",
-        "openai gpt",
-        "mcp openai",
-        "mcp server"
-      ],
-      "category": "aggregators"
-    },
     "TheLunarCompany--lunar": {
       "owner": "TheLunarCompany",
       "name": "lunar",
@@ -244,30 +220,6 @@
       ],
       "category": "aggregators"
     },
-    "hamflx--imagen3-mcp": {
-      "owner": "hamflx",
-      "name": "imagen3-mcp",
-      "url": "https://github.com/hamflx/imagen3-mcp",
-      "imageUrl": "",
-      "description": "A powerful image generation tool using Google's Imagen 3.0 API through MCP. Generate high-quality images from text prompts with advanced photography, artistic, and photorealistic controls.",
-      "stars": 43,
-      "forks": 7,
-      "license": "No License",
-      "language": "Rust",
-      "updated_at": "2025-09-20T19:36:59Z",
-      "readme_content": "# Imagen3-MCP\n\n[English Version](#imagen3-mcp-english)\n\n基于 Google 的 Imagen 3.0 的图像生成工具，通过 MCP（Model Control Protocol）提供服务。\n\n## 效果\n\n画一只奔跑的杰克罗素犬，长焦镜头，阳光透过狗狗的毛发，照片级画质\n\n\n\n画一个科技感十足的苹果\n\n\n\n## 安装要求\n\n- 有效的 [Google Gemini API 密钥](https://aistudio.google.com/apikey)\n\n## 安装步骤——Cherry Studio\n\n1. 从 [GitHub Releases](https://github.com/hamflx/imagen3-mcp/releases) 下载最新版本的可执行文件\n2. 将下载的可执行文件放置在系统中的任意位置，例如 `C:\\bin\\imagen3-mcp.exe`\n3. 在 Cherry Studio 中配置：\n   - Command 字段填写可执行文件路径，例如 `C:\\bin\\imagen3-mcp.exe`\n   - 环境变量 `GEMINI_API_KEY` 中填写你的 Gemini API 密钥\n   - [可选] 环境变量 `BASE_URL` 中填写代理地址，例如 `https://lingxi-proxy.hamflx.dev/api/provider/google`（这个地址可以解决 GFW 的问题，但是解决不了 Google 对 IP 的限制问题，因此还是得挂梯子）。\n   - [可选] 环境变量 `SERVER_LISTEN_ADDR`：设置服务器监听的 IP 地址（默认为 `127.0.0.1`）。\n   - [可选] 环境变量 `SERVER_PORT`：设置服务器监听的端口和图片 URL 使用的端口（默认为 `9981`）。\n   - [可选] 环境变量 `IMAGE_RESOURCE_SERVER_ADDR`：设置图片 URL 中使用的服务器地址（默认为 `127.0.0.1`）。这在服务器运行在容器或远程机器上时很有用。\n\n\n\n## 安装步骤——Cursor\n\n```json\n{\n  \"mcpServers\": {\n    \"imagen3\": {\n      \"command\": \"C:\\\\bin\\\\imagen3-mcp.exe\",\n      \"env\": {\n        \"GEMINI_API_KEY\": \"<GEMINI_API_KEY>\"\n        // Optional environment variables:\n        // \"BASE_URL\": \"<PROXY_URL>\",\n        // \"SERVER_LISTEN_ADDR\": \"0.0.0.0\", // Example: Listen on all interfaces\n        // \"SERVER_PORT\": \"9981\",\n        // \"IMAGE_RESOURCE_SERVER_ADDR\": \"your.domain.com\" // Example: Use a domain name for image URLs\n      }\n    }\n  }\n}\n```\n\n## 许可证\n\nMIT\n\n---\n\n# Imagen3-MCP (English)\n\nAn image generation tool based on Google's Imagen 3.0, providing services through MCP (Model Control Protocol).\n\n## Examples\n\nA running Jack Russell Terrier, telephoto lens, sunlight filtering through the dog's fur, photorealistic quality\n\n\n\nA high-tech apple\n\n\n\n## Requirements\n\n- Valid [Google Gemini API key](https://aistudio.google.com/apikey)\n\n## Installation Steps—Cherry Studio\n\n1. Download the latest executable from [GitHub Releases](https://github.com/hamflx/imagen3-mcp/releases)\n2. Place the downloaded executable anywhere in your system, e.g., `C:\\bin\\imagen3-mcp.exe`\n3. Configure in Cherry Studio:\n   - Fill in the Command field with the executable path, e.g., `C:\\bin\\imagen3-mcp.exe`\n   - Enter your Gemini API key in the `GEMINI_API_KEY` environment variable\n   - [Optional] Enter a proxy URL in the `BASE_URL` environment variable, e.g., `https://your-proxy.com`.\n   - [Optional] Set the `SERVER_LISTEN_ADDR` environment variable: The IP address the server listens on (defaults to `127.0.0.1`).\n   - [Optional] Set the `SERVER_PORT` environment variable: The port the server listens on and uses for image URLs (defaults to `9981`).\n   - [Optional] Set the `IMAGE_RESOURCE_SERVER_ADDR` environment variable: The server address used in the image URLs (defaults to `127.0.0.1`). Useful if the server runs in a container or remote machine.\n\n\n\n## Installation Steps—Cursor\n\n```json\n{\n  \"mcpServers\": {\n    \"imagen3\": {\n      \"command\": \"C:\\\\bin\\\\imagen3-mcp.exe\",\n      \"env\": {\n        \"GEMINI_API_KEY\": \"<GEMINI_API_KEY>\"\n        // Optional environment variables:\n        // \"BASE_URL\": \"<PROXY_URL>\",\n        // \"SERVER_LISTEN_ADDR\": \"0.0.0.0\", // Example: Listen on all interfaces\n        // \"SERVER_PORT\": \"9981\",\n        // \"IMAGE_RESOURCE_SERVER_ADDR\": \"your.domain.com\" // Example: Use a domain name for image URLs\n      }\n    }\n  }\n}\n```\n\n## License\n\nMIT",
-      "npm_url": "",
-      "npm_downloads": 0,
-      "keywords": [
-        "imagen3",
-        "imagen",
-        "images",
-        "imagen3 mcp",
-        "imagen api",
-        "google imagen"
-      ],
-      "category": "aggregators"
-    },
     "julien040--anyquery": {
       "owner": "julien040",
       "name": "anyquery",