What is imagen-tools-mcp AGENTS.md?

Repository instructions for an MCP server that generates and edits images with Google Gemini on Windows, macOS, and Linux.

Setting up, configuring, and maintaining the image-generation server and choosing between Vertex AI and AI Studio providers.

They document the required Python packages, Google authentication options, configuration, and a known limitation with one editing setup.

How hwalde/imagen-tools-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to hwalde/imagen-tools-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/hwalde/imagen-tools-mcp/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/hwalde/imagen-tools-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/hwalde/imagen-tools-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/hwalde/imagen-tools-mcp/agents-md)

Your own site

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

Per session 1,609 This file is loaded in full into every session.

When invoked 1,609 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	$0.01609	$0.01609
Opus 5.5	$0.00644	$0.00644
Sonnet 5.5	$0.00322	$0.00322
Haiku 4.5	$0.00161	$0.00161

Measured 2mo ago against content hash e22ccb70004f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

imagen-tools-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 · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Imagen Tools MCP — Setup & Konfiguration

Diese Datei ist die einzige Quelle der Projekt-Doku. CLAUDE.md importiert sie per @AGENTS.md, damit Claude Code sie automatisch mitlädt — nicht duplizieren, hier pflegen.

MCP-Server (stdio, Python) für Bildgenerierung und -bearbeitung mit Google Gemini. Läuft auf Windows, macOS und Linux.

Was der Server braucht

Baustein	Zweck	Pflicht?
Python ≥ 3.10	Laufzeit	ja
`google-genai`, `mcp`, `Pillow`	siehe `requirements.txt`	ja
Google-Cloud-Projekt mit aktivierter Vertex AI API	Provider `vertex_ai`	ja, für Vertex
`gcloud` CLI + Application Default Credentials	Auth für `vertex_ai`	ja, für Vertex
Gemini-API-Key (AI Studio)	Provider `ai_studio`	nur für AI Studio

Der Server unterstützt zwei Provider, zwischen denen zur Laufzeit gewechselt werden kann:

vertex_ai (Default) — authentifiziert über gcloud, zuverlässig für alle Operationen.
ai_studio — authentifiziert über API-Key, aber Bild-Editing mit dem Flash-Modell schlägt hier reproduzierbar mit 500 Internal Error fehl. Für Editing über AI Studio das Pro-Modell wählen oder auf vertex_ai wechseln.

Installation

pip install -r requirements.txt

Ein venv ist optional — wo systemweites pip erlaubt ist, genügt der Aufruf oben.

Konfiguration über Umgebungsvariablen

Projekt-ID und API-Key kommen ausschließlich aus der Umgebung — keine Zugangsdaten im Code. Gesetzt werden sie am besten direkt im env-Block des MCP-Eintrags (siehe unten), dann gelten sie nur für diesen Server und überleben Shell-Neustarts.

Nicht über die Umgebung steuerbar, sondern im Code festgelegt: Start-Provider und -Modell (DEFAULT_PROVIDER, DEFAULT_MODEL — zur Laufzeit über die switch_*-Tools änderbar), das 90-s-Timeout pro API-Call und MAX_INPUT_EDGE (1568 px).

Variable	Bedeutung	Default
`GOOGLE_CLOUD_PROJECT`	GCP-Projekt-ID. Ohne diese Variable startet der Server nicht (bei Provider `vertex_ai`).	—
`GEMINI_API_KEY_NANO_BANANA`	API-Key für Provider `ai_studio`.	leer
`IMAGEN_MCP_DEBUG`	`0` schaltet das Debug-Log ab.	`1` (an)
`IMAGEN_MCP_LOG_FILE`	Voller Pfad zur Log-Datei.	siehe unten

Read the full file on GitHub · 153 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 · 153 lines · 1,609 tokens per session scan A e22ccb70004f

Subscribe to this mod's changes

imagen-tools-mcp AGENTS.md is an instructions file published in the GitHub repository hwalde/imagen-tools-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,609 tokens to every session, about $0.0064 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

imagen-tools-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
imagen-tools-mcp AGENTS.mdhwalde/imagen-tools-mcp	Instructions file	0	3mo ago	MIT	A	1,609	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
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-tools-mcp: Instructions file for Codex