Agent Ready Mcp

What it does

The Agent Ready MCP skill equips your AI agent with the tools to audit any website for AI readiness. It installs the official Model Context Protocol (MCP) server, allowing your agent to run deep scans, retrieve historical reports, and query the Agent Ready knowledge base directly through native tool calls.

Why use this skill

Modern AI agents struggle with websites designed only for humans. This skill automates the technical discovery required to make your site "agent-friendly." By integrating via MCP, your agent avoids manual HTTP wiring or curl commands and gains access to specialized prompts for interpreting scan results and generating remediation plans.

Supported tools & workflows

• scan_site: Validates 60+ agent-readability signals (llms.txt, manifests, etc.).
• get_scan: Retrieves existing reports using a scan ID for historical comparison.
• ask: A local RAG tool to query definitions for specific agent-readability checks.
• Workflow Prompts: High-level wrappers for scanning, interpretation, and building prioritized fix-it docs.

Professional output

The skill produces structured summaries including an overall readability score (0–100), rating bands (e.g., "Excellent"), and a breakdown of failing technical checks with specific "How to Fix" instructions.