agentmods.dev

claude_openai_image_mcp: Instructions file for Claude Code

CLAUDE.md

claude_openai_image_mcp CLAUDE.md is an instructions file for Claude Code from theosera/claude_openai_image_mcp. It costs 851 tokens per session, scanned A, original, MIT.

Project instructions for a local server that creates images through OpenAI’s Images API and returns them to an MCP-compatible agent.

In plain words
What is it for?
Use it when changing, testing, or reviewing the image-generation MCP server.
Why use it?
It gives the agent clear rules for the codebase, including its TypeScript setup, safety limits, testing, and image-provider design.

Instructions file for Claude Code

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

This is theosera/claude_openai_image_mcp's own configuration. It tells Claude Code how to work on claude_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 claude_openai_image_mcp configures →

not rated 0repo 2d ago A scan 851 tokens original MIT
View source ↗ theosera/claude_openai_image_mcp
Reuse

Borrowing it

Nothing to install: this file belongs to theosera/claude_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/theosera/claude_openai_image_mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/theosera/claude_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 claude_openai_image_mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/theosera/claude_openai_image_mcp/claude-md/github.svg)](https://agentmods.dev/instructions/theosera/claude_openai_image_mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/theosera/claude_openai_image_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/theosera/claude_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 claude_openai_image_mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/theosera/claude_openai_image_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/theosera/claude_openai_image_mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 851 This file is loaded in full into every session.
When invoked 851 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 $0.00851 $0.00851
Opus 5 $0.00426 $0.00426
Sonnet 5 $0.00170 $0.00170
Haiku 4.5 $0.00085 $0.00085

Measured 9d ago against content hash 3abc0c189ad1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

claude_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 9d 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 — claude_openai_image_mcp

Local MCP server that generates images via the OpenAI Images API (gpt-image-2) and returns them as MCP image content. Server-side API key only; mock provider by default (no network, no billing).

Stack & commands

  • TypeScript, ESM, Node ≥ 22.12, pnpm. MCP: @modelcontextprotocol/sdk. Validation: zod.
  • pnpm run dev (tsx) · pnpm run build · pnpm test (vitest) · pnpm run lint:ox · pnpm run format:check · pnpm run lint · pnpm run typecheck
  • CI mirrors this order in .github/workflows/node.js.yml (+ CodeQL). Keep it green.

Architecture

  • src/config.ts — secret-free AppConfig (provider, model, allowlists, defaults). Fail-closed.
  • src/limits.ts — numeric bounds (prompt length, timeout, retries, concurrency, image bytes).
  • src/imageProvider.ts — ImageProvider interface, MockImageProvider, createProvider factory.
  • src/openaiImageClient.ts — live OpenAI Images call (official SDK). Typed 429/Retry-After/ timeout/5xx mapping; injectable ImagesApi seam so tests mock-reproduce every branch.
  • src/providerContract.ts — plugin contract (PROVIDER_API_VERSION, loader, version handshake). Exported as claude-openai-image-mcp/provider. Fail-closed on any load/handshake error.
  • src/providerGuard.ts — uniform guard around EVERY provider: timeout+abort, strict base64/magic-byte/MIME/size validation, identity pinning, redacted error surfacing.
  • src/server.ts — buildMcpServer + the single generate_image tool (validation/allowlist here).
  • src/index.ts — stdio entrypoint. src/logging.ts — stderr-only, redacting logger (keys, base64, JWT).

Invariants (do not break)

  • API key is server-side only. Never put it in AppConfig, logs, tool output, or JSON.stringify.
  • Allowlist before provider call. Validate size/quality/output_format up front; server picks the model.
  • Logs = metadata only. No prompt text, no image base64. The logger redacts key/base64 as defense in depth.
  • Mock stays the default. No live OpenAI call / billing without explicit user approval.
  • Plugin lane is opt-in and detachable. Activation requires BOTH IMAGE_MCP_PROVIDER=plugin and IMAGE_MCP_PROVIDER_MODULE; no plugin ever becomes a build-time dependency of the core. No automatic fallback between lanes (a broken plugin must never silently bill the API lane).
  • Provider output is untrusted. Every provider goes through providerGuard (timeout, base64/magic-byte/MIME/size checks, identity pinning, error redaction). Don't bypass it.
  • .env and generated images are git-ignored. Only .env.example (empty values) is committed.

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. 9d ago First seen · 52 lines · 851 tokens per session scan A 3abc0c189ad1

Subscribe to this mod's changes

claude_openai_image_mcp CLAUDE.md is an instructions file published in the GitHub repository theosera/claude_openai_image_mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 851 tokens to every session, about $0.0043 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

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

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