openai-image-mcp: Instructions file for Claude Code

CLAUDE.md

openai-image-mcp CLAUDE.md is an instructions file for Claude Code from aigentive/openai-image-mcp. It costs 879 tokens per session, scanned A, original, MIT.

A Claude Code instruction file for an OpenAI image MCP server, including setup, testing, packaging, and architecture notes.

In plain words
What is it for?
Use it to install dependencies, run tests and coverage, format or package the Python project, start the server locally, and test it with Claude Code.
Why use it?
It gives the coding agent the repository's development commands and explains how its conversation-based server is organised.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

agentmods badge for openai-image-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aigentive/openai-image-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/aigentive/openai-image-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/aigentive/openai-image-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aigentive/openai-image-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.

agentmods 80×15 button for openai-image-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/aigentive/openai-image-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aigentive/openai-image-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 879 This file is loaded in full into every session.
When invoked 879 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 $0.00879 $0.00879
Opus 5.5 $0.00352 $0.00352
Sonnet 5.5 $0.00176 $0.00176
Haiku 4.5 $0.00088 $0.00088

Measured 2mo ago against content hash fd4051397db9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openai-image-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 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 · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 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.

Development Commands

Environment Setup

# Install dependencies
poetry install

# Run tests
poetry run pytest

# Run specific test file
poetry run pytest tests/test_server.py

# Run with coverage
poetry run pytest --cov=src/openai_image_mcp

# Code formatting
poetry run black .
poetry run isort .

Package Operations

# Build package
poetry build

# Publish to PyPI
poetry publish

# Version bump
poetry version patch  # or minor/major

MCP Server Testing

# Run server locally
poetry run python -m openai_image_mcp.server

# Test with Claude Code
claude --mcp-config mcp-config.private.json --mcp-debug

Core Architecture

Session-Based Conversational Design

The system is built around multi-turn conversations with persistent memory, not traditional stateless API calls. Key architectural patterns:

  • Session Manager: Thread-safe session lifecycle with O(1) UUID lookup
  • Conversation Builder: Automatic context trimming at 50 turns, preserves image references
  • Responses API Client: Uses OpenAI Responses API (requires openai>=1.82.0) with exponential backoff retry logic
  • File Organizer: Structured storage with comprehensive metadata preservation

Component Interaction Flow

  1. MCP Tool Call → server.py (13 available tools)
  2. Session Creation → session_manager.py (UUID-based, thread-safe)
  3. Context Building → conversation_builder.py (multi-turn history)
  4. API Call → responses_client.py (OpenAI Responses API with tools)
  5. Image Processing → image_processor.py (download, save, metadata)
  6. File Organization → file_organizer.py (structured directories, metadata JSON)

MCP Tools Organization

Session Management (5 tools): create_image_session, generate_image_in_session, get_session_status, list_active_sessions, close_session

Image Generation (5 tools): generate_image, edit_image, generate_product_image, generate_ui_asset, analyze_and_improve_image

Read the full file on GitHub · 105 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. 2mo ago First seen · 105 lines · 879 tokens per session scan A fd4051397db9

Subscribe to this mod's changes

openai-image-mcp CLAUDE.md is an instructions file published in the GitHub repository aigentive/openai-image-mcp (1 stars, last pushed 1y ago), licensed MIT. It adds 879 tokens to every session, about $0.0035 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.

Related

openai-image-mcp CLAUDE.md compared with instructions from other repositories

openai-image-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
openai-image-mcp CLAUDE.mdaigentive/openai-image-mcpInstructions file11y agoMITA879Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144kyesterdayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot
generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginnersInstructions file124ktodayMITA2,981Codex, OpenCode