# Agent Readiness Auditor

> Agent Readiness Auditor is a free MCP server for ai models and llm tooling. Score a website for AI-agent safety, llms.txt and machine-readable signals. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Free
- **Platforms:** CLI, Web
- **Website:** https://scan.asishsingh.in
- **Repository:** https://github.com/asish-singh/agent-readiness-auditor
- **MCP Registry name:** io.github.asish-singh/agent-readiness-auditor
- **Categories:** AI models and LLM tooling, marketing and SEO, security
- **Listing updated:** 2026-11-15

## About

This package scores a site from 0 to 100 and gives a letter grade, with safety weighted most heavily. The biggest check, worth 40 points, looks for hidden prompt-injection text on every crawled page, including CSS-hidden content, zero-width characters, text in alt, title and aria-label attributes, and HTML comments.

The other eight checks cover llms.txt, robots.txt rules for AI crawlers such as GPTBot and ClaudeBot, JSON-LD, accountability links, a sitemap, FAQ-style structured data, meta robots, and an informational MCP signal that looks at /.well-known/ai-catalog.json for server and agent cards. It fetches the landing page, robots.txt, llms.txt, the sitemap and the AI Catalog, then crawls a few key pages.

The author also published a study auditing 84 prominent sites: none carried hidden injection content, 13% published FAQ structured data and none advertised an MCP endpoint. A separate hosted scanner offers a free visibility report by email.

## Features

- **Prompt-injection scan:** Looks for hidden agent-hijacking text across crawled pages.
- **llms.txt check:** Is there a curated site map for agents.
- **AI crawler stance:** Reads robots.txt rules for AI bots.
- **Structured data:** JSON-LD and FAQ or HowTo markup.
- **MCP signal:** Notes server and agent cards in the AI catalog.
- **Letter grade:** Weighted score from A to F.

## Good for

- Audit a site before launch for agent safety
- See whether llms.txt and JSON-LD are present
- Compare competitor sites
- Add a check to a CI pipeline

## Install

### Claude Code (Terminal)

```sh
claude mcp add agent-readiness-auditor -- npx -y agent-readiness-auditor
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "agent-readiness-auditor": {
      "command": "npx",
      "args": [
        "-y",
        "agent-readiness-auditor"
      ]
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "agent-readiness-auditor": {
      "command": "npx",
      "args": [
        "-y",
        "agent-readiness-auditor"
      ]
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "agent-readiness-auditor": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "agent-readiness-auditor"
      ]
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "agent-readiness-auditor": {
      "command": "npx",
      "args": [
        "-y",
        "agent-readiness-auditor"
      ]
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "agent-readiness-auditor": {
      "command": "npx",
      "args": [
        "-y",
        "agent-readiness-auditor"
      ]
    }
  }
}
```

## FAQ

### How is the score weighted?

Hidden prompt injection is 40 of 100 points; llms.txt, robots and JSON-LD 12 each.

### Does it change my site?

The hosted scanner says it checks public pages only.

### How do I run it?

With npx agent-readiness-auditor followed by a domain.

### Is the MCP check scored?

No. It is informational.

### Is Agent Readiness Auditor free?

Yes. Agent Readiness Auditor is free to use.

### How do I add Agent Readiness Auditor to Claude Code?

Run this command in your terminal: claude mcp add agent-readiness-auditor -- npx -y agent-readiness-auditor

### What are the best alternatives to Agent Readiness Auditor?

The closest alternatives to Agent Readiness Auditor are REA, Claude Code Ultimate Guide, Google Ads + Meta Ads + SEO/GEO MCP, Agent Roast and Midplane.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Google Ads + Meta Ads + SEO/GEO MCP](https://ai-powered.com/mcp/google-ads-meta-ads-seo-geo-mcp): Google Ads + Meta Ads + SEO/GEO MCP is a freemium MCP server for marketing and seo.
- [Agent Roast](https://ai-powered.com/mcp/agent-roast): Agent Roast is an open-source MCP server for developer tools.
- [Midplane](https://ai-powered.com/mcp/midplane): Midplane is an open-source MCP server for databases.
- [Calven](https://ai-powered.com/mcp/calven): Calven is an MCP server for marketing and seo.
- [Leash](https://ai-powered.com/mcp/leash): Leash is a free MCP server for security.
- [Tinplate Edge AI Safety, Security & EU Compliance](https://ai-powered.com/mcp/tinplate-edge-ai-safety-security-and-eu-compliance): Tinplate Edge AI Safety, Security & EU Compliance is a freemium MCP server for security.

---
Source: https://ai-powered.com/mcp/agent-readiness-auditor
