Pdf Toolkit Mcp
A full-featured PDF toolkit that handles both reads and writes through 22 tools. It extracts text and metadata, converts PDFs to Markdown with column clustering and heading inference, and renders pages to images so vision models can parse scanned documents. On the write side it creates PDFs from Markdown or templates, fills and flattens AcroForm fields, merges and splits while preserving form data, applies AES-256 encryption, and embeds QR codes or watermarks. Everything runs through WASM or pure JavaScript, so npx works across platforms without native dependencies or compilation. Runs offline, no API keys required.
- GitHub stars
- 7
- tools
- 22
- transport
- STDIO
- last updated
- May 29, 2026
Tools
22 toolsPublic tool metadata for what this MCP can expose to an agent.
pdf_extract_textExtract text from PDF pages (first 10 by default)
Extract text from PDF pages (first 10 by default)
No parameter schema in public metadata yet.
pdf_get_metadataGet title, author, subject, page count, dates, producer, and file size
Get title, author, subject, page count, dates, producer, and file size
No parameter schema in public metadata yet.
pdf_get_form_fieldsList form fields (text, checkbox, dropdown, radiogroup, listbox, button, signature) with names, types, values, and required status
List form fields (text, checkbox, dropdown, radiogroup, listbox, button, signature) with names, types, values, and required status
No parameter schema in public metadata yet.
pdf_to_markdownConvert a PDF to reading-order Markdown (column clustering, heading inference, list detection)
Convert a PDF to reading-order Markdown (column clustering, heading inference, list detection)
No parameter schema in public metadata yet.
pdf_searchFind text across pages and return page numbers with surrounding snippets (literal, case-insensitive by default)
Find text across pages and return page numbers with surrounding snippets (literal, case-insensitive by default)
No parameter schema in public metadata yet.
pdf_comparePage-by-page text diff between two PDFs
Page-by-page text diff between two PDFs
No parameter schema in public metadata yet.
pdf_mergeMerge multiple PDFs into one (preserves form fields)
Merge multiple PDFs into one (preserves form fields)
No parameter schema in public metadata yet.
pdf_splitExtract a page range into a new PDF (preserves form fields)
Extract a page range into a new PDF (preserves form fields)
No parameter schema in public metadata yet.
pdf_delete_pagesDelete a page range and keep the rest (preserves form fields)
Delete a page range and keep the rest (preserves form fields)
No parameter schema in public metadata yet.
pdf_reorder_pagesReorder pages in any order, duplicates allowed (preserves form fields)
Reorder pages in any order, duplicates allowed (preserves form fields)
No parameter schema in public metadata yet.
pdf_rotate_pagesRotate pages by 90, 180, or 270 degrees
Rotate pages by 90, 180, or 270 degrees
No parameter schema in public metadata yet.
pdf_flattenBake form-field values into static content (removes interactivity)
Bake form-field values into static content (removes interactivity)
No parameter schema in public metadata yet.
pdf_encryptAES-256 password protection with user and owner passwords
AES-256 password protection with user and owner passwords
No parameter schema in public metadata yet.
pdf_add_page_numbersAdd page numbers (configurable position, format, start, and size; rotation-aware)
Add page numbers (configurable position, format, start, and size; rotation-aware)
No parameter schema in public metadata yet.
pdf_embed_qr_codeEmbed a QR code or barcode (QR, Code128, DataMatrix, EAN-13, PDF417, Aztec; rotation-aware)
Embed a QR code or barcode (QR, Code128, DataMatrix, EAN-13, PDF417, Aztec; rotation-aware)
No parameter schema in public metadata yet.
pdf_createCreate a PDF from plain text (page size A4, Letter, or Legal; non-Latin via fontPath)
Create a PDF from plain text (page size A4, Letter, or Legal; non-Latin via fontPath)
No parameter schema in public metadata yet.
pdf_create_from_markdownCreate a rich PDF from Markdown: headings, tables, lists, code, blockquotes (A4, Letter, or Legal)
Create a rich PDF from Markdown: headings, tables, lists, code, blockquotes (A4, Letter, or Legal)
No parameter schema in public metadata yet.
pdf_create_from_templateCreate a PDF from a named template (invoice, report, letter)
Create a PDF from a named template (invoice, report, letter)
No parameter schema in public metadata yet.
pdf_fill_formFill form fields (text, checkbox, dropdown, radiogroup, listbox; non-Latin via fontPath)
Fill form fields (text, checkbox, dropdown, radiogroup, listbox; non-Latin via fontPath)
No parameter schema in public metadata yet.
pdf_add_watermarkAdd a diagonal text watermark to pages
Add a diagonal text watermark to pages
No parameter schema in public metadata yet.
pdf_embed_imageEmbed a PNG or JPEG image into a page
Embed a PNG or JPEG image into a page
No parameter schema in public metadata yet.
pdf_render_pagesRender pages to PNG or JPEG files, or return inline images a vision model can read directly
Render pages to PNG or JPEG files, or return inline images a vision model can read directly
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
PDF Toolkit MCP
💼 Available for freelance MCP/AI integration work — DM @aryansalian03 or via aryanbv.com
A write-capable PDF toolkit for any MCP client. It provides 22 tools for reading, creating, rendering, transforming, and securing PDFs. That includes rendering pages to images so vision models can read scanned documents, building PDFs from Markdown or structured data, AES-256 encryption, and merge and split operations that keep form fields intact. There are no native dependencies, so it runs locally from a single npx command.
npx -y @aryanbv/pdf-toolkit-mcp
It needs no config files, API keys, Docker, or compiler, and it works offline.
Overview
Details
- Repository
- github.com/aryanbv/pdf-toolkit-mcp
- Categories
- Design & Creative, Documents & Knowledge
- Package
@aryanbv/pdf-toolkit-mcp- Transport
- STDIO
- Registry
- MCP registry, active
Related Design & Creative MCP servers
View all
Amazon Mcppangolinfo/pangolinfo-mcpAmazon data MCP: products, reviews, niches, WIPO design/IP + US litigation, AI search & trends.6stars
Rendex: Rendering API for Images, PDFs & Content Extractioncopperline-labs/rendex-mcpRender HTML, Markdown, or URLs to images, PDF, or branded artifacts; extract and watch pages.6stars
PixelForgefreema/pixelforge-mcpForge pixel art sprites, animations, tilesets and game assets with Google Gemini.6stars
MCP Bench Routerk1ta141k/mcp-bench-routerRoutes design tasks to designarena.ai's top-ranked model via OpenRouter across 14 categories.6stars
Polyxdvisualfart/polyxdWrite Polyxd UI documents, check them, and show them as real screens in any design-system pack.5stars
AgentFXagentfxhq/agentfxMotion graphics and video effects your AI agent can script, lint, preview and render.4stars