Allows GitHub Copilot to read and visually analyze local documents (PDFs, Excel, Word, PowerPoint, images, etc.) through MCP tools.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Docalyze describe the trend shown in the chart on slide 2 of presentation.pptx"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An 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.
No API keys required. The host AI (GitHub Copilot, Claude, etc.) does all the reasoning directly.
Format | Extensions | Read | Visual |
| ✅ | ✅ | |
Excel |
| ✅ | ✅ |
CSV / TSV |
| ✅ | — |
JSON |
| ✅ | — |
Word |
| ✅ | ✅ |
PowerPoint |
| ✅ | ✅ |
Plain text |
| ✅ | — |
Images |
| — | ✅ |
Related MCP server: MCP PDF Reader
Tool | Description |
| List files under a directory, filtered by glob pattern |
| Get metadata (size, modified date, sheets) for a file |
| Extract text content from a document with pagination |
| Return page images inline so the AI can analyze charts, tables, and diagrams |
Search for docalyze in the MCP server gallery (Extensions sidebar → MCP tab) and click Install.
pip install docalyze-mcp-servernpx docalyze-mcp-serverThis requires uv or pipx installed — the npm wrapper calls uvx to run the Python package automatically.
Add to your VS Code mcp.json (or settings.json):
{
"servers": {
"docalyze": {
"type": "stdio",
"command": "python",
"args": ["-m", "docalyze_mcp_server"],
"env": {
"PYTHONIOENCODING": "utf-8"
}
}
}
}Or, if you installed via pip and want to use the entry point:
{
"servers": {
"docalyze": {
"type": "stdio",
"command": "docalyze-mcp-server"
}
}
}The base install handles PDF, Excel, CSV, JSON, and plain text. For additional formats:
# Word documents
pip install docalyze-mcp-server[docx]
# PowerPoint
pip install docalyze-mcp-server[pptx]
# OCR (requires Tesseract installed on your system)
pip install docalyze-mcp-server[ocr]
# Everything
pip install docalyze-mcp-server[all]The server reads documents from a configurable root directory. Set the DOCUMENTS_ROOT environment variable to change it:
{
"servers": {
"docalyze": {
"type": "stdio",
"command": "docalyze-mcp-server",
"env": {
"DOCUMENTS_ROOT": "/path/to/your/documents"
}
}
}
}If not set, it defaults to the directory containing the server script.
MIT
Return metadata about a specific document.
Inputs: file_path (required). Returns: result
List documents under the configured root directory.
Inputs: root, pattern, limit. Returns: result
Read a portion of a document (PDF, Excel, CSV, JSON, TXT, DOCX).
IMPORTANT: When presenting results to users, ALWAYS mention:
The folder/directory path (e.g., 'Well 1/Well Test/')
The complete document name This helps users understand which well and document type is being referenced.
Inputs: file_path (required), max_chars, page, max_pages, +4 more. Returns: result
Extract visual content from a document (PDF pages or images) and return it as inline images so the host AI can analyse charts, tables, and diagrams directly. Optionally run local Tesseract OCR as well.
Returns a list of content blocks (text and/or base64 images) that the calling AI model can interpret.
Inputs: file_path (required), enable_ocr, page, max_pages, +1 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 4 tools
Each tool has a distinct purpose: metadata retrieval, listing, text reading, and visual analysis. No two tools overlap in functionality.
All tools use snake_case and end with 'document' or 'documents', but 'document_info' is a noun-noun pattern while others are verb-noun, causing minor inconsistency.
Four tools is a reasonable scope for a document analysis server, covering essential read operations without being excessive.
The tools cover metadata, listing, text reading, and visual analysis. However, folder navigation or search is missing, which may be needed given the mention of directory structure.
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
