What is imagen-mcp AGENTS.md?

Repository instructions for imagen-mcp, a Python server that lets clients use image-generation providers through the Model Context Protocol, a standard way for AI tools to call external capabilities. They describe the project layout, commands, coding rules, and tests.

Use them when developing, formatting, type-checking, or testing imagen-mcp, including its provider selection, configuration, request models, server, and compatibility code.

They give an AI coding assistant the project-specific rules needed to change the repository consistently and check that changes still work.

How michaeljabbour/imagen-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to michaeljabbour/imagen-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/michaeljabbour/imagen-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/michaeljabbour/imagen-mcp

Made for: Codex, OpenCode.

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/michaeljabbour/imagen-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/michaeljabbour/imagen-mcp/agents-md)

Your own site

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

Per session 665 This file is loaded in full into every session.

When invoked 665 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	$0.00665	$0.00665
Opus 5.5	$0.00266	$0.00266
Sonnet 5.5	$0.00133	$0.00133
Haiku 4.5	$0.00067	$0.00067

Measured 2mo ago against content hash ff4eda7aa509, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

imagen-mcp AGENTS.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.

AGENTS.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

For contributors building and maintaining the MCP image generation server.

Project Structure & Module Organization

imagen_mcp is the canonical package and python -m imagen_mcp is the MCP entry point. src is an identity-preserving compatibility namespace.
src/providers/ holds provider implementations (openai_provider.py, gemini_provider.py), selector.py for auto-selection, and registry.py for factory wiring.
src/config/ contains constants and settings; src/models/input_models.py defines Pydantic request models.
Tests live in tests/ mirroring modules (test_selector.py, test_providers.py, test_server.py); run.sh is the wrapper used by MCP clients; dependencies are declared in pyproject.toml.

Build, Test, and Development Commands

Install locked development dependencies: uv sync --extra dev.
Run the server locally: uv run python -m imagen_mcp (or ./run.sh when invoked by clients); export at least one provider API key first.
Format and lint: uv run ruff format imagen_mcp src tests && uv run ruff check imagen_mcp src tests.
Type check: uv run mypy imagen_mcp src.
Tests: uv run pytest (verbosity and discovery configured in pytest.ini).
Build and smoke distributions: uv build, then clean-install the wheel/sdist and run tests/installed_distribution_smoke.py outside the checkout.

Coding Style & Naming Conventions

Python 3.10+; Ruff line length 100; prefer explicit imports and typed signatures (mypy is strict: no implicit Optional, no untyped defs).
Use snake_case for modules/functions, PascalCase for classes; keep provider IDs consistent with registry keys (openai, gemini).
Keep side effects out of import time; guard script entry with if __name__ == "__main__": when needed.

Testing Guidelines

Add or extend tests in tests/ near the related module using the test_*.py/Test*/test_* pattern.
Mock external APIs—reuse dummy env vars as in tests/test_selector.py; avoid live requests in CI.
Cover new branching in provider selection, config defaults, and tool metadata (reasoning, confidence, alternatives) when relevant.

Read the full file on GitHub · 38 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.

2mo ago First seen · 38 lines · 665 tokens per session scan A ff4eda7aa509

Subscribe to this mod's changes

imagen-mcp AGENTS.md is an instructions file published in the GitHub repository michaeljabbour/imagen-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 665 tokens to every session, about $0.0027 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.

imagen-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
imagen-mcp AGENTS.mdmichaeljabbour/imagen-mcp	Instructions file	0	4mo ago	MIT	A	665	Codex, OpenCode
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

imagen-mcp: Instructions file for Codex