{
  "markdown": "<!-- mcp-name: io.github.LunarPerovskite/docalyze -->\n<p align=\"center\">\n  <img src=\"logo.svg\" alt=\"Docalyze Logo\" width=\"150\" height=\"150\">\n</p>\n\n# Docalyze MCP Server\n\nAn MCP (Model Context Protocol) server that lets AI assistants read and visually analyze local documents — PDFs, Excel spreadsheets, CSV files, Word documents, PowerPoint presentations, and images.\n\nNo API keys required. The host AI (GitHub Copilot, Claude, etc.) does all the reasoning directly.\n\n## Supported Formats\n\n| Format | Extensions | Read | Visual |\n|--------|-----------|:----:|:------:|\n| PDF | `.pdf` | ✅ | ✅ |\n| Excel | `.xlsx`, `.xls` | ✅ | ✅ |\n| CSV / TSV | `.csv`, `.tsv` | ✅ | — |\n| JSON | `.json` | ✅ | — |\n| Word | `.docx` | ✅ | ✅ |\n| PowerPoint | `.pptx` | ✅ | ✅ |\n| Plain text | `.txt`, `.md` | ✅ | — |\n| Images | `.png`, `.jpg`, `.jpeg`, `.gif`, `.bmp`, `.tiff`, `.webp` | — | ✅ |\n\n## Tools\n\n| Tool | Description |\n|------|-------------|\n| `list_documents` | List files under a directory, filtered by glob pattern |\n| `document_info` | Get metadata (size, modified date, sheets) for a file |\n| `read_document` | Extract text content from a document with pagination |\n| `visual_evaluate_document` | Return page images inline so the AI can analyze charts, tables, and diagrams |\n\n## Installation\n\n### From VS Code (recommended)\n\nSearch for **docalyze** in the MCP server gallery (Extensions sidebar → MCP tab) and click Install.\n\n### From PyPI\n\n```bash\npip install docalyze-mcp-server\n```\n\n### From npm\n\n```bash\nnpx docalyze-mcp-server\n```\n\nThis requires [uv](https://docs.astral.sh/uv/) or pipx installed — the npm wrapper calls `uvx` to run the Python package automatically.\n\n### Manual setup\n\nAdd to your VS Code `mcp.json` (or `settings.json`):\n\n```jsonc\n{\n  \"servers\": {\n    \"docalyze\": {\n      \"type\": \"stdio\",\n      \"command\": \"python\",\n      \"args\": [\"-m\", \"docalyze_mcp_server\"],\n      \"env\": {\n        \"PYTHONIOENCODING\": \"utf-8\"\n      }\n    }\n  }\n}\n```\n\nOr, if you installed via pip and want to use the entry point:\n\n```jsonc\n{\n  \"servers\": {\n    \"docalyze\": {\n      \"type\": \"stdio\",\n      \"command\": \"docalyze-mcp-server\"\n    }\n  }\n}\n```\n\n## Optional Dependencies\n\nThe base install handles PDF, Excel, CSV, JSON, and plain text. For additional formats:\n\n```bash\n# Word documents\npip install docalyze-mcp-server[docx]\n\n# PowerPoint\npip install docalyze-mcp-server[pptx]\n\n# OCR (requires Tesseract installed on your system)\npip install docalyze-mcp-server[ocr]\n\n# Everything\npip install docalyze-mcp-server[all]\n```\n\n## Configuration\n\nThe server reads documents from a configurable root directory. Set the `DOCUMENTS_ROOT` environment variable to change it:\n\n```jsonc\n{\n  \"servers\": {\n    \"docalyze\": {\n      \"type\": \"stdio\",\n      \"command\": \"docalyze-mcp-server\",\n      \"env\": {\n        \"DOCUMENTS_ROOT\": \"/path/to/your/documents\"\n      }\n    }\n  }\n}\n```\n\nIf not set, it defaults to the directory containing the server script.\n\n## License\n\nMIT\n",
  "bytes": 2947,
  "sha": "f303e86a8c431f2d15eabdc342ff9781f902dd381008276bee1837863583802f",
  "repo_slug": "lunarperovskite/docalyze-mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_lunarperovskite_docalyze_09f7967c/readme"
}