pdf-redaction-mcp: Instructions file for GitHub Copilot

.github/copilot-instructions.md

pdf-redaction-mcp copilot-instructions.md is an instructions file for GitHub Copilot from marc-hanheide/pdf-redaction-mcp. It costs 1,540 tokens per session, scanned A, original, MIT.

Project-specific instructions for an MCP server that edits PDF files, including loading, extracting, searching, redacting, saving, and managing documents in memory. MCP is a standard way for AI agents to call tools.

In plain words
What is it for?
Use them when working on PDF text or image redaction, document sessions, file-path handling, or new MCP tools in this project.
Why use it?
They explain the server's architecture and document workflow, reducing mistakes when adding or changing PDF tools.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is marc-hanheide/pdf-redaction-mcp's own configuration. It tells GitHub Copilot how to work on pdf-redaction-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pdf-redaction-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to marc-hanheide/pdf-redaction-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.

Copy the file
curl -O https://raw.githubusercontent.com/marc-hanheide/pdf-redaction-mcp/master/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/marc-hanheide/pdf-redaction-mcp

Made for: GitHub Copilot.

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.

agentmods badge for pdf-redaction-mcp copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/marc-hanheide/pdf-redaction-mcp/copilot-instructions.svg)](https://agentmods.dev/instructions/marc-hanheide/pdf-redaction-mcp/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/marc-hanheide/pdf-redaction-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/marc-hanheide/pdf-redaction-mcp/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,540 This file is loaded in full into every session.
When invoked 1,540 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01540 $0.01540
Opus 5 $0.00770 $0.00770
Sonnet 5 $0.00308 $0.00308
Haiku 4.5 $0.00154 $0.00154

Measured 7d ago against content hash 80db193873a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pdf-redaction-mcp copilot-instructions.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 7d 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.

.github/copilot-instructions.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PDF Redaction MCP Server - AI Coding Instructions

Project Overview

A Model Context Protocol (MCP) server for PDF redaction using FastMCP 2.x and pymupdf. This server provides 11 tools for session-based PDF operations - load, extract, search, redact text/images, save, and manage documents in memory. Version 0.2.0.

Architecture

All tools register to a single mcp = FastMCP("PDF Redaction Server") instance at module level (server.py). Use @mcp.tool() decorator for all new tools.

Session-Based In-Memory Workflow

NEW in v0.2.0: Documents are loaded into memory once and operated on without repeated file I/O.

  • DOCUMENT_STORE dictionary: Maps document_id -> pymupdf.Document objects
  • Documents persist in memory across multiple operations
  • Explicit load_pdf() and save_pdf() for I/O control
  • Use close_pdf() to free memory when done

PDF Path Resolution

Only load_pdf() uses file paths. It uses resolve_pdf_path() to handle relative paths:

  • If --pdf-dir is set, relative paths are resolved against it
  • Absolute paths are used as-is
  • Global PDF_BASE_DIR variable stores the configured base directory

All other tools work with document_id instead of file paths.

Development Workflow

Environment Setup

# Install dependencies (uses UV package manager)
uv sync

# Run tests
uv run pytest

# Run server locally (STDIO mode - default)
uv run pdf-redaction-mcp

# Run server with different transports
uv run pdf-redaction-mcp --transport sse --port 8000
uv run pdf-redaction-mcp --transport http --host 0.0.0.0 --port 8080

# Run with custom PDF base directory
uv run pdf-redaction-mcp --pdf-dir /path/to/pdfs

# Combine options
uv run pdf-redaction-mcp --transport sse --port 8000 --pdf-dir ./documents

Testing Pattern

Tests in tests/test_server.py:

  • Import functions directly from pdf_redaction_mcp.server module
  • Handle FastMCP decoration: if hasattr(fn, 'fn'): fn = fn.fn
  • Test error handling with non-existent document IDs (should return JSON with "error" key)
  • No real PDF fixtures currently - tests focus on error handling and structure

Read the full file on GitHub · 198 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.

  1. 7d ago First seen · 198 lines · 1,540 tokens per session scan A 80db193873a6

Subscribe to this mod's changes

pdf-redaction-mcp copilot-instructions.md is an instructions file published in the GitHub repository marc-hanheide/pdf-redaction-mcp (0 stars, last pushed 7mo ago), licensed MIT. It adds 1,540 tokens to every session, about $0.0077 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 2026-09-01.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens