English Français العربية

Inlay

Official registry AI and agents

Make any website discoverable by AI agents via MCP, llms.txt, and structured data.

Source code Documentation

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

Remote (streamable-http)
Claude Code 
claude mcp add --transport http inlay 'https://inlay.dev/api/mcp/{site_key}'
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "inlay": {
            "type": "http",
            "url": "https://inlay.dev/api/mcp/{site_key}"
        }
    }
}
Remote (sse)
Claude Code 
claude mcp add --transport sse inlay 'https://inlay.dev/api/mcp/{site_key}'
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "inlay": {
            "type": "sse",
            "url": "https://inlay.dev/api/mcp/{site_key}"
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. Inlay Skills
  2. Install
  3. Skills
  4. Example Audit Output
  5. Why AI Readiness Matters
  6. Contributing
  7. License

Inlay Skills

AI Agent Skills for Website AI Readiness

Agent skills to audit and optimize any website for AI readiness — llms.txt, MCP servers, structured data, semantic HTML, and more.

Install

npx skills add cartoonitunes/inlay-skills

Works with Claude Code, Cursor, Codex, OpenCode, and 35+ other agents.

Skills

🔍 ai-readiness-audit

Audit any website for AI agent readiness using the Inlay API. Get a score out of 100, letter grade, per-category breakdown, and actionable recommendations.

> Audit https://example.com for AI readiness

What it checks:

  • llms.txt presence and quality
  • MCP server availability
  • Structured data (JSON-LD / schema.org)
  • Meta tags and Open Graph
  • Semantic HTML structure
  • AI bot permissions in robots.txt
  • Performance, security, accessibility
  • Content quality and AI signals
📄 setup-llms-txt

Create and configure llms.txt for your website. Analyzes your project, generates the file, and places it in the right location for your framework.

> Set up llms.txt for this project
🔌 setup-mcp-server

Set up an MCP (Model Context Protocol) server for your website via Inlay. Enables AI agents to search and interact with your site.

> Set up an MCP server for my website

Example Audit Output

📊 AI Readiness Score: 62/100 (C)

Category          Score   Status
llms.txt          0       ❌
MCP Server        0       ❌
Structured Data   45      ⚠️
Meta Quality      78      ✅
Semantic HTML     85      ✅
Robots & Crawling 60      ⚠️
Performance       72      ✅

🔧 Top Recommendations:
1. Create llms.txt (+15 points)
2. Set up MCP server via Inlay (+12 points)
3. Unblock AI bots in robots.txt (+8 points)

Why AI Readiness Matters

AI agents and AI search engines (ChatGPT, Perplexity, Claude, Gemini) are becoming primary ways people discover and interact with websites. Sites that are optimized for AI agents get:

  • Cited more often in AI search results
  • Better tool integration with AI assistants
  • Higher visibility as AI-first browsing grows

Inlay helps you measure and improve your AI readiness score.

Contributing

Contributions welcome! Open an issue or PR.

License

MIT

Frequently asked questions

What is Inlay?

Make any website discoverable by AI agents via MCP, llms.txt, and structured data.

How do I install Inlay?

It runs as a remote server. In Claude Code: claude mcp add --transport http inlay 'https://inlay.dev/api/mcp/{site_key}'. For other clients, paste the JSON configuration from this page into their MCP settings.

Does Inlay need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is Inlay open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains Inlay?

It is published by cartoonitunes. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.