What is invokeai-mcp AGENTS.md?

A set of project instructions for invokeai-mcp, an MCP project that connects an AI agent with InvokeAI, a local AI image-generation server.

Use it when developing, configuring, or reviewing the invokeai-mcp project and its connection to InvokeAI.

It gives the agent the project’s standards, important files, and available tool interface while making changes.

How sandraschi/invokeai-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to sandraschi/invokeai-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/sandraschi/invokeai-mcp/main/AGENTS.md

Clone the repo

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

Your own site

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

Per session 801 This file is loaded in full into every session.

When invoked 801 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	$0.00801	$0.00801
Opus 5.5	$0.00320	$0.00320
Sonnet 5.5	$0.00160	$0.00160
Haiku 4.5	$0.00080	$0.00080

Measured 2mo ago against content hash 25a676822392, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

invokeai-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 · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

invokeai-mcp — Agent Guide

Fleet MCP server (Creative / Image Generation). Wraps the local InvokeAI engine (port 9090). Ports 11154 (backend) / 11155 (frontend).

Overview

FastMCP 3.4+ bridge: generate (txt2img/img2img/inpaint/upscale), queue, models, gallery, boards, workflows + SOTA dark webapp. Onboarding required (InvokeAI must be installed + running + models installed) - MOCK-until-onboarded UI.

Standards

FastMCP 3.4.4+ portmanteau + skills (skill:// resource) + Prefab cards
Dual transport: stdio (default) + HTTP --mode http (MCP /mcp, REST /api/*)
Starlette 1.0 REST (no Pydantic in routes), fleet CORS on outer app
MCPB: just mcpb-pack (wipe+recopy src -> mcpb/src, 3-4-100 verified)
Onboarding: docs/ONBOARDING.md + red under-hero CTA + MOCK badges
No GitHub Actions while private; local just ci is the gate

Key files

Path	Role
`src/invokeai_mcp/server.py`	FastMCP + Starlette app, dual transport
`src/invokeai_mcp/client.py`	Typed InvokeAI REST client
`src/invokeai_mcp/graphs.py`	Graph builders (sd1/sdxl/flux, inpaint, esrgan upscale)
`src/invokeai_mcp/tools/`	7 portmanteaus + 4 Prefab cards + help/shutdown
`src/invokeai_mcp/api/routes.py`	REST routes (health, dashboard, skills, tools, logs, llm, generate, queue, upload, image proxy, plugins, hf login, engine control)
`src/invokeai_mcp/skills/invokeai-expert/`	SKILL.md
`webapp/`	Vite React + Tailwind dark UI + Playwright e2e

Quick ref

.\start.ps1
uv run pytest tests/ -q
cd webapp; bun run dev
just mcpb-pack   # fleet recipe (mcpb/pack.ps1)
just zombies     # dry-run port zombie sweep
just zombie-clean

Tool surface (portmanteau)

invokeai_generate (txt2img/img2img/inpaint/upscale/outpaint + seamless/ controlnet/ip-adapter modules + cogview4 family + styles=[...] + artists=[...] multi-dim batches - outpaint via webapp pad+mask), engine control (Settings) + HF token login (Settings + Models HF tab), invokeai_queue (status/list/item_status/result/cancel/clear/resume/pause), invokeai_models (list/get/install/installs/update/delete/stats), invokeai_gallery (list/search/get/metadata/download/delete/star/unstar), invokeai_boards, invokeai_styles (list/get/search/community - 1321 A1111 pack styles), invokeai_artists (list/get/search), invokeai_franchises (list/get/search), invokeai_workflows, invokeai_system (health/version/config/stats), 4 Prefab cards, invokeai_help, invokeai_shutdown.

Read the full file on GitHub · 62 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 · 62 lines · 801 tokens per session scan A 25a676822392

Subscribe to this mod's changes

invokeai-mcp AGENTS.md is an instructions file published in the GitHub repository sandraschi/invokeai-mcp (2 stars, last pushed 12d ago), licensed MIT. It adds 801 tokens to every session, about $0.0032 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.

ai-art flux image-generation invokeai mcp stable-diffusion

invokeai-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
invokeai-mcp AGENTS.mdsandraschi/invokeai-mcp	Instructions file	2	12d ago	MIT	A	801	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	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	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

invokeai-mcp: Instructions file for Codex