{
  "markdown": "# MinerU MCP Plugin README\n\nThis plugin enables Claude to extract high-precision structured data (Markdown, HTML, LaTeX, DOCX) from PDFs, images, and web pages using the MinerU API via the Model Context Protocol (MCP).\n\n## 🚀 Features\n\n- **Document Extraction:** Convert PDFs, images, and Word/PPTx files to structured Markdown.\n- **Web Extraction:** Fetch and convert remote web pages via URL.\n- **Precision Mode:** High-precision table recognition, formula recognition, and OCR.\n- **Flash Mode (Default):** Free, no authentication required, limited to 20 pages / 10 MB. **Used automatically if no API Token is set.**\n\n## 🛠️ Setup\n\n### Important Notice\n\n> **未设置 API Token，将使用 Flash 模式（免费，无需认证，限 20 页 / 10 MB）。如需完整功能，请设置 MINERU_API_TOKEN 环境变量。**\n\nThis plugin supports automatic fallback to Flash Mode. If you do not provide a `MINERU_API_TOKEN`, it will default to the free tier.\n\n### Required Environment Variables\n\nTo unlock full functionality (Precision Mode), set your API token:\n\n```bash\nexport MINERU_API_TOKEN=\"your-token-here\"\n```\n\n### Obtaining Tokens\n\n1. Visit [https://mineru.net/api-keys](https://mineru.net/api-keys) (official MinerU API Token page).\n2. Create a new API token.\n3. Set the `MINERU_API_TOKEN` environment variable.\n\n## ⚙️ MCP Configuration\n\nYour MCP config (e.g., `claude_desktop_config.json` or `mcp.json`) should remain as follows. The `env` field will pass the environment variable you set to the MinerU MCP server:\n\n```json\n{\n  \"mcpServers\": {\n    \"mineru\": {\n      \"type\": \"streamableHttp\",\n      \"url\": \"https://mcp.mineru.net/mcp\",\n      \"env\": {\n        \"MINERU_API_TOKEN\": \"your token\"\n      }\n    }\n  }\n}\n```\n\n## 📂 Directory Structure\n\n```text\nmineru-claude-plugin/\n├── .claude-plugin/\n│   └── plugin.json      # Plugin metadata\n├── .mcp.json            # MCP server configuration\n├── skills/              # Skill definitions\n│   └── mineru-extract/\n│       ├── skill.json   # Skill metadata\n│       └── SKILL.md     # Skill instructions\n└── README.md            # Documentation\n```\n\n## 📖 Usage\n\nOnce configured, Claude can use the following capabilities through the Mineru MCP server:\n\n### 1. Document Extraction\n- **Flash Extract:** Fast conversion for files up to 10 MB and 20 pages.\n- **Precision Extract:** High-precision mode requiring an API token, supporting tables and formulas.\n\n### 2. Web Extraction\n- **Crawl:** Convert content from a URL to Markdown or HTML.\n\n## ❓ Troubleshooting\n\n- **Authentication Errors:** If you see 401 Unauthorized, verify your token.\n- **Flash Mode Fallback:** If you are not using a token, ensure your file is within the 20 pages / 10 MB limit.\n- **Feature Limits:** Flash Mode does not support complex table/formula recognition. Use Precision Mode for these features.\n\n## 🔗 Resources\n\n- [MinerU Website](https://mineru.net/)\n- [MinerU Extract Skill](https://clawhub.ai/mineru-extract/mineru-document-extractor)\n- [Claude Plugins Documentation](https://github.com/anthropics/claude-plugins-official)\n",
  "bytes": 2981,
  "sha": "060635637aef59951f84ce81e28f0114fe9bfd90c10494d6d8d1aa79b7ecf62e",
  "repo_slug": "decrystal/mineru-claude-plugin",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_decrystal_mineru_claude_plugin_mineru_do_01d2a8e4/readme"
}