What is nutrient-pdf-mcp-server CLAUDE.md?

Repository-specific instructions for a PDF MCP server that lets agents inspect the internal object structure of PDF files. It explains the project, its architecture, and tools for navigating and resolving PDF objects.

Setting up the project and investigating PDF object trees, including selected paths or objects, with shallow or deeper resolution.

It helps an agent understand how to use and modify the server while keeping large PDF structures manageable through on-demand loading.

How PSPDFKit/nutrient-pdf-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to PSPDFKit/nutrient-pdf-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/PSPDFKit/nutrient-pdf-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/PSPDFKit/nutrient-pdf-mcp-server

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/pspdfkit/nutrient-pdf-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/pspdfkit/nutrient-pdf-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/pspdfkit/nutrient-pdf-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/pspdfkit/nutrient-pdf-mcp-server/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/pspdfkit/nutrient-pdf-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/pspdfkit/nutrient-pdf-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 758 This file is loaded in full into every session.

When invoked 758 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00758	$0.00758
Opus 5.5	$0.00303	$0.00303
Sonnet 5.5	$0.00152	$0.00152
Haiku 4.5	$0.00076	$0.00076

Measured 2mo ago against content hash 2539b416adce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nutrient-pdf-mcp-server 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 2mo 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.

CLAUDE.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nutrient PDF MCP Server - Claude Memory

Project Overview

This is the Nutrient PDF MCP Server, a Model Context Protocol (MCP) server for investigating PDF object trees with lazy loading support. The server allows LLMs to explore PDF structure efficiently by providing selective resolution of indirect objects and path-based navigation.

Key Features

Lazy Loading: Only resolves indirect objects on demand to reduce token usage
Path Navigation: Supports dot notation paths like Pages.Kids.0 for drilling down
Two Resolution Modes: Shallow (single object) and deep (with dependencies)
Type Safety: Comprehensive TypedDict definitions for all PDF objects
Error Handling: Custom exception hierarchy with detailed error messages

Architecture

pdf_mcp/server.py - Main MCP server with two tools
pdf_mcp/parser.py - Core PDF parsing logic with pypdf integration
pdf_mcp/types.py - Type definitions for PDF objects and responses
pdf_mcp/exceptions.py - Custom exception hierarchy

MCP Tools

get_pdf_object_tree - Get JSON representation of PDF structure
- Parameters: pdf_path, mode (lazy/full), path (optional), object_id (optional)
resolve_indirect_object - Resolve specific indirect objects by ID
- Parameters: pdf_path, object_id, depth (shallow/deep)

Development

Python 3.10+ required (for MCP library pattern matching)
Use make commands for common tasks:
- make test - Run test suite (64 tests)
- make test-cov - Run tests with coverage analysis
- make quality - Run all quality checks (format, lint, type check, test)
- make format - Auto-format code with black/isort
- make lint - Check code with ruff
- make typecheck - Type check with mypy

Quality Standards

76% test coverage with comprehensive test suite
Full type checking with mypy (custom overrides for pypdf interactions)
Modern Python syntax (union types with |, lowercase builtins)
Code formatting with black, isort, ruff

Read the full file on GitHub · 86 lines

Changes

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.

2mo ago First seen · 86 lines · 758 tokens per session scan A 2539b416adce

Subscribe to this mod's changes

nutrient-pdf-mcp-server CLAUDE.md is an instructions file published in the GitHub repository PSPDFKit/nutrient-pdf-mcp-server (5 stars, last pushed 2mo ago), licensed MIT. It adds 758 tokens to every session, about $0.0030 per session on Opus 5.5. 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.

Documents PDF ai-integration llm-tools mcp pdf-parser pdf-tools

nutrient-pdf-mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
nutrient-pdf-mcp-server CLAUDE.mdPSPDFKit/nutrient-pdf-mcp-server	Instructions file	5	2mo ago	MIT	A	758	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	280k	2d ago	MIT	A	4,325	Codex, OpenCode

nutrient-pdf-mcp-server: Instructions file for Claude Code