Pdf Toolkit MCP

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…

People connecting web framework tools to Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.

VERIFIED ACTIVE

LAST COMMIT 2026-07-22 · ★ 9 · #21 OF 48 MAINTAINED WEB FRAMEWORK · VERIFIED 2026-08-25

MIT · TypeScript servers · how we verify → /methodology

01 · Install Pdf Toolkit MCP

before you install - you'll need

The README does not document required environment variables for a basic install.

Claude Code

claude mcp add aryanbv-pdf-toolkit-mcp -- npx -y @aryanbv/pdf-toolkit-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "aryanbv-pdf-toolkit-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@aryanbv/pdf-toolkit-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

npm package @aryanbv/pdf-toolkit-mcp - published under the repo owner's npm scope (@aryanbv)

registry namespace io.github.AryanBV is GitHub-verified and matches the repo owner

03 · What Pdf Toolkit MCP can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can extract text from PDF pages (first 10 by default), get title, author, subject, page count, dates, producer, and file size, list form fields (text, checkbox, dropdown, radiogroup, listbox, button, signature) with names, types, values, and required status, and convert a PDF to reading-order Markdown (column clustering, heading inference, list detection).

The 22 tools it gives your agent

Extracted from the project's README - what pdf-toolkit-mcp lets an agent do.

pdf_extract_text
- Extract text from PDF pages (first 10 by default)
pdf_get_metadata
- Get title, author, subject, page count, dates, producer, and file size
pdf_get_form_fields
- List form fields (text, checkbox, dropdown, radiogroup, listbox, button, signature) with names, types, values, and required status
pdf_to_markdown
- Convert a PDF to reading-order Markdown (column clustering, heading inference, list detection)
pdf_search
- Find text across pages and return page numbers with surrounding snippets (literal, case-insensitive by default)
pdf_compare
- Page-by-page text diff between two PDFs
pdf_merge
- Merge multiple PDFs into one (preserves form fields)
pdf_split
- Extract a page range into a new PDF (preserves form fields)
pdf_delete_pages
- Delete a page range and keep the rest (preserves form fields)
pdf_reorder_pages
- Reorder pages in any order, duplicates allowed (preserves form fields)
pdf_rotate_pages
- Rotate pages by 90, 180, or 270 degrees
pdf_flatten
- Bake form-field values into static content (removes interactivity)
show all 22 tools
pdf_encrypt
- AES-256 password protection with user and owner passwords
pdf_add_page_numbers
- Add page numbers (configurable position, format, start, and size; rotation-aware)
pdf_embed_qr_code
- Embed a QR code or barcode (QR, Code128, DataMatrix, EAN-13, PDF417, Aztec; rotation-aware)
pdf_create
- Create a PDF from plain text (page size A4, Letter, or Legal; non-Latin via fontPath)
pdf_create_from_markdown
- Create a rich PDF from Markdown: headings, tables, lists, code, blockquotes (A4, Letter, or Legal)
pdf_create_from_template
- Create a PDF from a named template (invoice, report, letter)
pdf_fill_form
- Fill form fields (text, checkbox, dropdown, radiogroup, listbox; non-Latin via fontPath)
pdf_add_watermark
- Add a diagonal text watermark to pages
pdf_embed_image
- Embed a PNG or JPEG image into a page
pdf_render_pages
- Render pages to PNG or JPEG files, or return inline images a vision model can read directly

Latest releases

v0.3.1 · 2026-05-29

Documentation-only release. No runtime or API changes from 0.3.0; the published package is functionally identical. · This release exists so the npm package page carries the rewritten README. The README was rewritten in…

v0.3.0 · 2026-05-29

Prism is an incremental, pre-1.0 release. It grows the toolkit from 16 to 22 tools, rebuilds PDF creation on @react-pdf/renderer, upgrades encryption to AES-256, and adds real quality infrastructure (test suite…

v0.2.0 · 2026-04-01

What's new · 6 new tools (16 total) · pdf_create_from_markdown - Create professional PDFs from Markdown with headings, tables, lists, bold/italic, code blocks, and page numbers · pdf_create_from_template - Generate…

04 · Who maintains Pdf Toolkit MCP

pdf-toolkit-mcp is maintained by aryanbv. It's the only MCP server we track from this author; the repo dates to Mar 2026.

05 · Facts

category
web framework - ranked #21 of 48 actively-maintained web framework servers as of 2026-08-25.
release cadence
2 releases in the last 90 days (latest 2026-05-29)
registry
io.github.AryanBV/pdf-toolkit-mcp (active, first published 2026-04-01 · 4 versions)
packages
npm:@aryanbv/pdf-toolkit-mcp

06 · Pdf Toolkit MCP FAQ

Is Pdf Toolkit MCP still maintained?

Yes - as of 2026-08-25, its last commit was 2026-07-22 and it shipped 2 releases in the last 90 days. We re-verify nightly.

What can Pdf Toolkit MCP do?

With this server connected, an agent can extract text from PDF pages (first 10 by default), get title, author, subject, page count, dates, producer, and file size, list form fields (text, checkbox, dropdown, radiogroup, listbox, button, signature) with names, types, values, and required status, and convert a PDF to reading-order Markdown (column clustering, heading inference, list detection).

How do I install Pdf Toolkit MCP?

Run `npx -y @aryanbv/pdf-toolkit-mcp`. The README does not document required environment variables for a basic install. You can also paste the ready-made client config above.

Does Pdf Toolkit MCP run locally?

Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Pdf Toolkit MCP