LLM Integration Guide

Documentation for AI assistants and LLMs on how to use Inliner.ai for image generation.

For AI Assistants: This page explains how to integrate Inliner.ai into your responses. Use the machine-readable files below for quick reference.

Machine-Readable Files

Following the llms.txt standard, we provide these files for AI systems:

llms.txt

Concise summary of Inliner.ai for quick LLM reference. Contains URL format, quick start, and essential links.

View /llms.txt

llms-full.txt

Comprehensive documentation including all integration methods, MCP tools, pricing, and complete code examples.

View /llms-full.txt

URL Format

The core concept: describe an image in a URL, get back a generated image.

URL Structure

https://img.inliner.ai/{project}/{description}_{width}x{height}.{format}

Example:
https://img.inliner.ai/demo/happy-dog-playing-fetch_800x600.png

Smart URL behavior: In MCP/CLI generation flows, long prompts are summarized into concise URL slugs by default while preserving full generation quality.

Integration Methods

Direct URL — Use URLs directly in HTML/CSS
MCP Server — For Claude Code, Cursor, Copilot, Gemini CLI
CLI — npx @inliner/cli "sunset-beach-palm-trees_1200x600.png"
REST API — Programmatic access via api.inliner.ai

Edit vs Generate Modality

For image changes, route to edit workflows with source context. Requests like "make it 600x600" can be interpreted as new generation if no source URL/path is provided.

Edit existing image: Use edit_image (MCP) or inliner-ai edit ... (CLI) with explicit source
Generate new image: Use generate_image/generate_image_url (MCP) or inliner-ai generate ... (CLI)
If ambiguous: Ask whether to edit the previous image or create a new one

Cursor MCP Config (Recommended)

.cursor/mcp.json

{
  "mcpServers": {
    "inliner": {
      "command": "npx",
      "args": ["@inliner/mcp-server"],
      "env": {
        "INLINER_API_KEY": "${INLINER_API_KEY}",
        "INLINER_DEFAULT_PROJECT": "your-project-namespace"
      }
    }
  }
}

Project-Specific Instructions

Users can get customized LLM instructions for their specific projects:

Log into the Inliner dashboard
Go to Projects
Click LLM Instructions on any project
Copy instructions optimized for Claude, Cursor, ChatGPT, etc.

These instructions include the user's namespace, custom prompts, and reference images.