What is graphics-mcp CLAUDE.md?

An MCP server for image editing, where MCP is a standard way for AI tools to call external services. It can inspect, convert, resize, crop, rotate, flip, filter, and thumbnail images while restricting which files it may access.

Use it to process images, create thumbnails, apply effects such as blur or grayscale, and run a local HTTP service for these operations.

It gives an agent a controlled way to perform common image operations without allowing unrestricted access to the filesystem.

How lesleslie/graphics-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lesleslie/graphics-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/lesleslie/graphics-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lesleslie/graphics-mcp

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/lesleslie/graphics-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/lesleslie/graphics-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/lesleslie/graphics-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lesleslie/graphics-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.

Your own site · 80×15

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

Per session 1,174 This file is loaded in full into every session.

When invoked 1,174 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	$0.01174	$0.01174
Opus 5.5	$0.00470	$0.00470
Sonnet 5.5	$0.00235	$0.00235
Haiku 4.5	$0.00117	$0.00117

Measured 1mo ago against content hash 9d112aedaede, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

graphics-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 1mo 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 · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 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 this repository.

For a shorter, tool-neutral bootstrap document, start with AGENTS.md.

Project Overview

graphics-mcp is a unified MCP server for graphics manipulation with multiple backends, providing image processing capabilities via the Model Context Protocol.

Key Dependencies: Python 3.13+, mcp-common, Pillow/pilkit

Core Features

Image Operations: Get info, convert, resize, crop, rotate, flip
Filters: Apply effects (blur, sharpen, grayscale, etc.)
Thumbnails: Generate thumbnails with configurable sizes
Security: Path validation, file size limits, allowed directories

Most Common Commands

# Start HTTP MCP server (factory default)
graphics-mcp start

# Run local health probe
graphics-mcp health

The server is bound via environment variables: GRAPHICS_HTTP_HOST and GRAPHICS_HTTP_PORT (defaults 127.0.0.1 and 3040). Allowed directories are configured via GRAPHICS_ALLOWED_DIRECTORIES (JSON array form, e.g. '["/tmp", "/Users/les/Pictures", "/Users/les/Downloads"]').

Critical Rules

1. SECURITY IS NON-NEGOTIABLE

NEVER allow arbitrary file paths
ALWAYS validate paths against allowed directories
ALWAYS enforce file size limits
NEVER expose internal filesystem structure

2. PATH VALIDATION

All image paths must be within allowed directories
Use GRAPHICS_ALLOWED_DIRECTORIES environment variable
Validate before any file operation

3. NO PLACEHOLDERS - EVER

NEVER use dummy data orplaceholder images
ALWAYS use proper configuration

4. MCP-COMMON PATTERNS

Follow mcp-common patterns for server lifecycle
Use MCPServerCLIFactory for CLI commands
Inherit from base settings classes

Configuration

Set via environment variables with GRAPHICS_ prefix:

Variable	Description	Default
`GRAPHICS_ALLOWED_DIRECTORIES`	JSON-array list of allowed paths (e.g. `'["/tmp", "/data"]'`)	-
`GRAPHICS_MAX_FILE_SIZE_MB`	Maximum file size	100

Read the full file on GitHub · 130 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.

1mo ago Changed · +3 lines · +45 tokens per session 9d112aedaede
2mo ago Changed · +21 lines · +236 tokens per session 2ef713f2c1f6
2mo ago First seen · 106 lines · 893 tokens per session scan A a880ada8f775

Subscribe to this mod's changes

graphics-mcp CLAUDE.md is an instructions file published in the GitHub repository lesleslie/graphics-mcp (1 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 1,174 tokens to every session, about $0.0047 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.

Creative and media

graphics-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
graphics-mcp CLAUDE.mdlesleslie/graphics-mcp	Instructions file	1	1mo ago	BSD-3-Clause	A	1,174	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	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

graphics-mcp: Instructions file for Claude Code