Create, read, transform, secure, and render PDFs through 22 local MCP tools.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent โ or use 1-click editor setup below.
This server is confirmed live โ we successfully called its tools/list endpoint directly (see the verified badge above). We haven't yet sandbox-tested the stdio install command below specifically, which is a separate, ongoing check.
๐ก Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Pdf Toolkit MCP.
pdf_extract_textExtract text content from a PDF file. Returns first 10 pages by default to avoid exceeding LLM context limits. Use the 'pages' parameter for specific pages.
pdf_get_metadataGet metadata from a PDF file including title, author, subject, page count, creation/modification dates, and producer information.
pdf_get_form_fieldsList all form fields in a PDF with their names, types, current values, and required status. Returns hasForm: false for PDFs without forms.
pdf_to_markdownConvert a PDF to clean, reading-order Markdown for LLM consumption: reconstructs up to 2 content columns (plus full-width title/footer bands), infers headings from font size, and detects bullet/numbered lists. Pages with 3 or more columns fall back to single-column reading order. Tables are emitted as plain reading-order text, NOT reconstructed as Markdown tables. Best on clean, digital (text-based) PDFs; degrades on scanned/image-only PDFs (use pdf_render_pages for those) and very complex layouts. Returns the first 10 pages by default.
pdf_searchSearch text across a PDF and return matches with a short surrounding snippet and the page number. The query is matched as a literal substring (case-insensitive by default). Searches all pages unless a range is given.
pdf_mergeMerge multiple PDF files into one. AcroForm fields are preserved; fields whose names collide across inputs are auto-renamed (namespaced by source). Set flatten:true to bake field values into static content.
AryanBV/pdf-toolkit-mcp MCP server provides 22 tools for working with PDF files through an MCP client. Its capabilities cover four broad workflows: inspecting existing documents, changing their structure or content, generating new PDFs, and rendering pages for visual review.
For document inspection, the server can extract text, return metadata, list AcroForm fields, search for literal text matches, convert text-based PDFs to reading-order Markdown, and compare two PDFs page by page. The Markdown conversion can infer headings and detect lists, but it does not reconstruct tables as Markdown tables.
Creation tools support plain text, CommonMark and GFM Markdown, and three named templates: invoice, report, and letter. Other tools fill form fields, add watermarks or images, insert QR codes and barcodes, and add page numbers. Existing files can be merged, split, reordered, rotated, or have pages deleted. Form values can be flattened into static page content, and PDFs can be protected with AES-256 password encryption.
The AryanBV/pdf-toolkit-mcp MCP server runs as a local stdio process. An MCP client starts the package with npx, then selects tools and supplies their arguments. Operations generally use input and output file paths, while read-oriented tools return extracted information in the MCP response. Rendering can either write PNG or JPEG files and return their paths, or return inline image blocks for a vision-capable client.
Most text extraction tools return the first 10 pages by default to limit response size. Page ranges or page lists can be supplied where supported. PDF transformations preserve AcroForm fields for merge, split, reorder, and delete operations; duplicate field names from merged inputs are automatically namespaced. Flattening removes field interactivity after baking current values into the page content.
Install requirements are limited to Node.js 20 or newer and an MCP client that supports local server processes. No API key, configuration file, Docker container, compiler, or native dependency is required. The server is described as working on Windows, macOS, and Linux.
Run it directly with:
Claude Desktop, Cursor, and Windsurf can connect by adding a server entry that uses npx with -y and @aryanbv/pdf-toolkit-mcp as the package argument. Claude Code and VS Code Agent mode are also documented in the source material, but their configuration formats differ from the other clients.
The AryanBV/pdf-toolkit-mcp MCP server includes these practical operations:
Plain-text creation and form filling accept a font path for non-Latin text such as Arabic or CJK. QR and barcode insertion supports QR code, Code 128, Data Matrix, EAN-13, PDF417, and Aztec formats.
PDF-to-Markdown works best with clean, digital, text-based documents. Scanned or image-only PDFs need pdf_render_pages, and complex layouts may not convert accurately. The converter handles up to two content columns plus full-width title or footer bands; documents with three or more columns fall back to single-column reading order.
PDF comparison uses absolute page indexes and content-stream text order rather than visual reading order. Reflowed or multi-column documents can therefore produce noisy differences, and inserting or deleting a page shifts subsequent comparisons. Large responses may be truncated. Off-page placements are rejected rather than silently clipped, and deleting every page is not allowed.
Factual signals from GitHub, npm, and our automated checks โ not a rating.
No reviews yet โ be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/aryanbv-pdf-toolkit-mcp)<a href="https://allmcps.com/mcp/aryanbv-pdf-toolkit-mcp"><img src="https://allmcps.com/api/badge/aryanbv-pdf-toolkit-mcp?style=directory" alt="Pdf Toolkit MCP on AllMCPs" /></a>