Borrowing it
Nothing to install: this file belongs to AryanBV/pdf-toolkit-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AryanBV/pdf-toolkit-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/AryanBV/pdf-toolkit-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/aryanbv/pdf-toolkit-mcp/claude-md)<a href="https://agentmods.dev/instructions/aryanbv/pdf-toolkit-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aryanbv/pdf-toolkit-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/aryanbv/pdf-toolkit-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aryanbv/pdf-toolkit-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.06576 | $0.06576 |
| Opus 5 | $0.03288 | $0.03288 |
| Sonnet 5 | $0.01315 | $0.01315 |
| Haiku 4.5 | $0.00658 | $0.00658 |
Grade A, and why
pdf-toolkit-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pdf-toolkit-mcp
1. Project Overview
What: A write-capable, zero-config, TypeScript-native MCP server for PDF manipulation. Provides 22 tools for reading, modifying, creating, and rendering PDFs — including page-to-image rendering for vision-capable clients, high-fidelity Markdown→PDF, AES-256 encryption, and form-preserving merge/split — usable from any MCP client (Claude Code, Claude Desktop, etc.) with zero installation beyond npx. Ships 5 guided-workflow prompts and a templates resource.
Why: Learning MCP server development, building open-source credibility, and laying groundwork for Prevyl.
- Package:
@aryanbv/pdf-toolkit-mcp - Install:
npx -y @aryanbv/pdf-toolkit-mcp - License: MIT
- Repo: github.com/AryanBV/pdf-toolkit-mcp
2. Tech Stack
Multi-engine architecture: @pdfme/pdf-lib manipulates existing PDFs + @react-pdf/renderer driven by remark/mdast handles rich creation (Markdown, templates) + unpdf (pdf.js) reads text/metadata and positional text + @hyzyla/pdfium (WASM) renders pages to images + @neslinesli93/qpdf-wasm (WASM) does AES-256 encryption.
| Dependency | Version | Why |
|---|---|---|
| TypeScript | strict, ESM ("type": "module") |
Type safety, all .ts imports use .js extension (Node16 resolution) |
| Node.js | >= 20 | Conservative non-breaking floor (18 and 20.x are EOL); CI tests 20/22/24, 22 or 24 LTS recommended |
@modelcontextprotocol/sdk |
^1.29.0 | MCP protocol implementation. Use server.registerTool() — NOT .tool() (deprecated) |
@pdfme/pdf-lib |
^5.5.10 | Fork of abandoned pdf-lib. Existing PDF manipulation (merge, split, rotate, watermark, embed, page numbers, reorder, delete, flatten, QR) |
unpdf |
^1.4.0 | Text extraction, metadata, and positional text (pdf.js). Replaces pdfjs-dist which requires Node 22+ canvas bindings |
@react-pdf/renderer |
^4.5.1 | High-fidelity PDF creation for Markdown and templates (Helvetica default; custom TTF via Font.register). Lazy-loaded inside handlers |
react |
^19.2.6 | Peer of @react-pdf/renderer; document trees are built with React.createElement |
unified + remark-parse + remark-gfm |
^11 / ^11 / ^4 | Markdown → mdast AST (CommonMark + GFM tables/strikethrough) consumed by the react-pdf renderer |
mdast-util-to-markdown |
^2.1.2 | Serializes reconstructed layout nodes back to Markdown for pdf_to_markdown |
@hyzyla/pdfium |
^2.1.13 | PDFium compiled to WASM — renders PDF pages to raster bitmaps for pdf_render_pages. Zero native deps. Lazy-loaded |
@neslinesli93/qpdf-wasm |
^0.3.0 | qpdf compiled to WASM — AES-256 encryption for pdf_encrypt. Zero native deps. Lazy-loaded |
pngjs + jpeg-js |
^7.0.0 / ^0.4.4 | Encode PDFium raster bitmaps to PNG / JPEG buffers |
diff |
^9.0.0 | Line-level text diff for pdf_compare |
@bwip-js/node |
^4.8.0 | Barcode/QR code generation as PNG buffers. ESM — import { toBuffer } from '@bwip-js/node' |
fontkit |
^2.0.0 | Non-Latin font embedding for form filling. Use import fontkit from 'fontkit' — NOT @pdf-lib/fontkit (stale wrapper) |
zod |
^3.25.0 | Schema validation for tool inputs. Compatible with MCP SDK's ^3.25 || ^4.0 range |
| Transport | stdio | stdin/stdout protocol channel — console.log is forbidden |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 303 lines · 6,576 tokens per session scan A c677ae03ca42
pdf-toolkit-mcp CLAUDE.md is an instructions file published in the GitHub repository AryanBV/pdf-toolkit-mcp (9 stars, last pushed 1mo ago), licensed MIT. It adds 6,576 tokens to every session, about $0.0329 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.