A set of rules for using a local InvokeAI image-generation engine from the coding environment.

Use it to generate or edit images, install models, control image jobs, organise galleries, and manage workflows in InvokeAI.

It tells the agent what image creation, editing, model, queue, gallery, and workflow operations are available.

How sandraschi/invokeai-mcp configures Cursor

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/.cursorrules

Clone the repo

git clone --depth 1 https://github.com/sandraschi/invokeai-mcp

Made for: Cursor.

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/rules/sandraschi/invokeai-mcp/cursorrules/github.svg)](https://agentmods.dev/rules/sandraschi/invokeai-mcp/cursorrules)

Your own site

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

Per session 274 This file is loaded in full into every session.

When invoked 274 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	$0.00274	$0.00274
Opus 5.5	$0.00110	$0.00110
Sonnet 5.5	$0.00055	$0.00055
Haiku 4.5	$0.00027	$0.00027

Measured 2mo ago against content hash dfcc2c0f30c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cursorrules 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.

.cursorrules · 24 lines

What it actually says

Session Context (InvokeAI MCP)

You have access to the local InvokeAI creative engine: image generation (txt2img / img2img / masked inpaint / 4x upscale), queue control, model management (HF/Civitai installs), gallery/board organization, and workflow library management.

Before starting work:

Check engine health: invokeai_system(operation="health") - if configured is false, InvokeAI is not running; tell the user and point to docs/ONBOARDING.md, do not pretend generation works.
Check installed models: invokeai_models(operation="list", model_type="main")
- first entry is the default generation model.

At end of work, save outputs:

Download generated images locally: invokeai_queue(operation="result", item_id=..., download_image=true)
Organize favorites into boards: invokeai_boards(operation="add_image", board_id=..., image_names=[...])

Workflow: generate -> poll queue (result, wait_seconds) -> gallery -> download. Pitfalls: flux ignores negative prompts; outpaint is canvas-only (InvokeAI web UI); first generation is slow (model load); VRAM errors -> use SDXL/SD1.5 or lower resolution.

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 · 24 lines · 274 tokens per session scan A dfcc2c0f30c4

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository sandraschi/invokeai-mcp (2 stars, last pushed 12d ago), licensed MIT. It adds 274 tokens to every session, about $0.0011 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 ai-art flux image-generation invokeai mcp stable-diffusion

cursorrules next to 6 cursor rules from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cursorrulessandraschi/invokeai-mcp	Cursor rule	2	12d ago	MIT	A	274	Cursor
image-generationprenats/claude-imagine	Cursor rule	1	4mo ago	MIT	A	382	Cursor
prompt-to-assetMohamedAbdallah-14/prompt-to-asset	Cursor rule	24	19d ago	MIT	A	5,126	Cursor
generalsunra-ai/sunra-clients	Cursor rule	8	1mo ago	Apache-2.0	A	1,566	Cursor
cascade-imglaffeyp/cascade-img	Cursor rule	2	3mo ago	Apache-2.0	A	1,031	Cursor
ponytailDietrichGebert/ponytail	Cursor rule	185k	8d ago	MIT	A	604	Cursor
angular-20angular/angular	Cursor rule	101k	yesterday	MIT	A	0	Cursor

invokeai-mcp: Cursor rule for Cursor