mcp-image-extractor: Instructions file for Claude Code

CLAUDE.md

mcp-image-extractor CLAUDE.md is an instructions file for Claude Code from ifmelate/mcp-image-extractor. It costs 620 tokens per session, scanned A, original, MIT.

Project instructions for mcp-image-extractor, an MCP server that extracts images from files, web addresses, and base64 text for language-model analysis. It also documents the project’s commands and source structure.

In plain words
What is it for?
Use it when working on image extraction, image compression, the server’s three extraction tools, its TypeScript source, or its Jest tests.
Why use it?
It gives coding agents the project-specific information needed to build, test, lint, and modify the server consistently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is ifmelate/mcp-image-extractor's own configuration. It tells Claude Code how to work on mcp-image-extractor 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 mcp-image-extractor configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ifmelate/mcp-image-extractor. 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/ifmelate/mcp-image-extractor/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ifmelate/mcp-image-extractor

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.

agentmods badge for mcp-image-extractor CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ifmelate/mcp-image-extractor/claude-md.svg)](https://agentmods.dev/instructions/ifmelate/mcp-image-extractor/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ifmelate/mcp-image-extractor/claude-md"><img src="https://agentmods.dev/badge/instructions/ifmelate/mcp-image-extractor/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 620 This file is loaded in full into every session.
When invoked 620 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 $0.00620 $0.00620
Opus 5 $0.00310 $0.00310
Sonnet 5 $0.00124 $0.00124
Haiku 4.5 $0.00062 $0.00062

Measured 7d ago against content hash 81e44c064c1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-image-extractor 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 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.

CLAUDE.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

MCP (Model Context Protocol) server that extracts images from files, URLs, and base64 strings, converts them to base64, and returns them for LLM analysis. Published to npm as mcp-image-extractor.

Commands

npm run build        # Compile TypeScript → dist/ (also chmod +x dist/index.js)
npm run dev          # Run directly via ts-node (no build step)
npm start            # Run compiled server from dist/
npm run lint         # ESLint on .ts files
npm test             # Jest tests (--no-cache)

Run a single test file:

npx jest tests/compression.test.ts --no-cache

Architecture

Two source files with clear separation:

  • src/index.ts — MCP server setup. Registers three tools (extract_image_from_file, extract_image_from_url, extract_image_from_base64) using @modelcontextprotocol/sdk, validates inputs, and connects via stdio transport.

  • src/image-utils.ts — All image processing logic. Three main async functions (extractImageFromFile, extractImageFromUrl, extractImageFromBase64) plus compressImage helper. Uses sharp for resize/compress, axios for URL fetching. All images are resized to max 512x512 and compressed before base64 encoding to optimize LLM context usage.

Response format: Every tool returns McpToolResponse with a content array containing a text block (JSON metadata: width, height, format, size) and an image block (base64 data + mimeType).

Key Constants & Environment Variables

  • MAX_IMAGE_SIZE — Max input image size in bytes (default: 10MB / 10485760)
  • ALLOWED_DOMAINS — Comma-separated domain whitelist for URL extraction (default: empty = all allowed)
  • Default resize target: 512x512 pixels

Testing

Tests live in tests/. Jest config is in jest.config.js with ts-jest preset. Coverage is collected from src/**/*.ts excluding index.ts.

Read the full file on GitHub · 52 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 · 52 lines · 620 tokens per session scan A 81e44c064c1d

Subscribe to this mod's changes

mcp-image-extractor CLAUDE.md is an instructions file published in the GitHub repository ifmelate/mcp-image-extractor (21 stars, last pushed 6mo ago), licensed MIT. It adds 620 tokens to every session, about $0.0031 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 2026-08-30.