A Model Context Protocol server that reads, analyzes, creates, and edits PDF, DOCX, and Excel files. Give your AI agent full document intelligence with 10 specialized tools.
Extract text, understand structure, and answer questions about PDF, DOCX, and Excel files - including scanned documents via vision-based OCR.
Native text extraction for digital PDFs. Vision-based OCR for scanned documents with AI-powered post-processing that fixes broken words, spacing, and character errors.
Rich text extraction from Word documents preserving formatting and embedded images. Multi-sheet Excel parsing with full cell value extraction.
Don't just dump text - ask specific questions. The focused query tool lets AI agents interrogate documents for exactly the information they need.
Generate professional Word documents and Excel spreadsheets directly from AI conversations. Edit existing files without losing formatting.
Unlike naive approaches that rebuild documents from scratch, the edit-doc tool works directly with the XML inside the DOCX ZIP structure. This means edits preserve all original formatting - headers, footers, images, custom styles, and complex layouts remain intact when appending or replacing content.
Every capability is exposed as a Model Context Protocol tool that any MCP-compatible AI agent can use.
get-doc-summaryHigh-level document overview with structure, sections, and embedded images
get-doc-indepthFull text extraction with formatting, metadata, and embedded images
get-doc-focusedTargeted analysis answering specific questions about a document
create-docCreate Word documents with headings, tables, headers, footers, and 7 style presets
create-excelCreate Excel workbooks with multiple sheets, styling, and formatted headers
edit-docEdit DOCX files via XML patching - preserves original formatting, headers, and images
edit-excelAppend rows, add sheets, or replace data in existing Excel workbooks
check-documentPrevent duplicates with create/augment/replace guidance before writing
save-memoryPersist document preferences across sessions via Document DNA
delete-memoryRemove saved document preferences when no longer needed
Each preset defines a complete typographic system - fonts, sizes, heading levels, spacing, justification, and table styling. Documents can also be auto-styled by category.
Everyday, clean documents
11ptExecutive summaries, formal reports
11ptAPI docs, specs, user manuals
11ptContracts, agreements, legal briefs
12ptProposals, go-to-market plans
11ptInternal comms, team updates
12ptPresentations, marketing materials
12ptA built-in AI guidance system that learns your preferences, prevents duplicates, and automatically styles documents based on project identity.
A .document-dna.json config stores your company name, default style, headers, and footers. Every document inherits your brand automatically. Three-level inheritance: system defaults, project DNA, and user overrides.
Documents are automatically categorized by keywords into contracts, technical, business, legal, meeting, or research. Each category maps to the right style preset and folder structure.
A persistent registry tracks every document created for deduplication and discovery. Thread-safe with atomic file locking for concurrent access. No more accidentally creating the same report twice.
Built with the official MCP SDK in pure JavaScript. No frameworks, no build step - just a fast, focused server.
Built on @modelcontextprotocol/sdk. Works with Claude Code, LM Studio, Cline, Roo Code, and any MCP-compatible client.
Two vision providers with automatic failover - local LM Studio for privacy, or Z.AI cloud for higher accuracy.
DOCX edits work at the XML level inside the ZIP structure, preserving all original formatting during modifications.
File locking, placeholder files, and spin-wait retry for production-grade concurrent document creation.
MIT licensed. Install it, configure your AI agent, and start reading, creating, and editing documents in minutes.