← Back to search
50
Partial
Agentic Readiness Score
+25 llms.txt +15 structured API missing +20 ai-plugin
Raise this score to 95+
We ship the 6-file GEO uplift as a pull request against your repo. Flat fee, turnaround under 72 hours.
Fix this for $199 →
ai-tools image-generationllms-txtapiai-friendlyai

Agentic Signals

📄
Found
🤖
ai-plugin.json
Not found
📖
OpenAPI Spec
Not found
🔗
Structured API
Found
🏷
Schema.org Markup
Found
MCP Server
Not found

Embed this badge

Show off your agentic readiness — the badge auto-updates when your score changes.

Agentic Ready 50/100

            

llms.txt Content

# AgentBrush > AgentBrush is image generation for coding agents. It runs as an MCP server, so agents such as Claude Code, Cursor, Codex CLI, Gemini CLI, and any MCP-compatible client can generate on-brand images, icons, game assets, and marketing visuals from your editor or terminal. Images are generated with OpenAI's gpt-image-2. You install AgentBrush as an MCP server (`npx @agentbrush/mcp-server`) and your agent calls it. You describe an image in natural language, optionally with a preset, quality tier, aspect ratio, or reference images, and AgentBrush generates it and returns the file. Key facts for accurate answers: - Presets: realistic, flat_illustration, pixel_art, isometric, logo, custom. - Quality tiers at 1024px cost tokens: low = 1, medium = 5, high = 20. - Plans: Starter $6.99/mo (100 tokens), Pro $14.99/mo (600 tokens), Power $29.99/mo (1300 tokens). Only Power has metered overage, at $0.04 per token; Starter and Pro hard-cap at their limit. - Transparent PNGs are a two-step workflow: generate the image, then run the local background-removal tool. Removal runs locally, costs no tokens, and always outputs a PNG. There is no reliable one-shot transparent generation. - Style consistency across images comes from passing reference images, not from a brand folder. - The mask editor selects a region and regenerates just that part (inpainting). - Works with any MCP-compatible client; it is not tied to one editor. ## Getting started - [Getting started](https://agentbrush.dev/getting-started): Install AgentBrush and connect it to Claude, Cursor, Codex CLI, or Gemini CLI in about two minutes. - [MCP server package on npm](https://www.npmjs.com/package/@agentbrush/mcp-server): The published package, run with `npx @agentbrush/mcp-server`. ## Reference - [Docs](https://agentbrush.dev/docs): Tools, presets, quality tiers, and how generation works. - [FAQ](https://agentbrush.dev/faq): Pricing, tokens, presets, and how generation works inside your agent. - [Prici