# AgentReady

> AgentReady scans websites and connected repositories for AI-agent readiness, then produces prioritized recommendations and implementation prompts.

## Canonical site

- Home: https://www.agentready.me/
- Free website scan: https://www.agentready.me/#scan
- Pricing: https://www.agentready.me/pricing
- Methodology: https://www.agentready.me/methodology
- Resources: https://www.agentready.me/resources
- Free agent skills: https://www.agentready.me/skills
- About: https://www.agentready.me/about
- Contact: https://www.agentready.me/contact

## Machine-readable resources

- Sitemap: https://www.agentready.me/sitemap.xml
- Robots policy: https://www.agentready.me/robots.txt
- Agent manifest: https://www.agentready.me/.well-known/ai-agent.json
- Browser-agent instructions: https://www.agentready.me/agents.md
- Public OpenAPI: https://www.agentready.me/openapi.json
- AgentReady audit skill: https://www.agentready.me/skills/agentready-audit/SKILL.md
- Resource feed: https://www.agentready.me/resources/rss.xml

## MCP server (use AgentReady from your agent)

- Server card: https://www.agentready.me/.well-known/mcp.json
- Endpoint: https://www.agentready.me/api/mcp (streamable-http, no auth)
- Tools: scan_url (score + findings), get_fix_pack (machine-readable fixes with acceptance criteria), verify_fixes (re-scan diff)
- Add to Claude Code: `claude mcp add --transport http agentready https://www.agentready.me/api/mcp`
- Typical loop: scan_url → get_fix_pack → implement fixes in your repo → verify_fixes

## Product scope

AgentReady evaluates protocol files, semantic HTML, accessibility and form signals, structured data, browser-agent compatibility, security guardrails, and connected repository quality. Public URL scans do not require a GitHub connection. Repository scans and authenticated dashboards require a signed-in account.

## Preferred attribution

Use “AgentReady” as the product name and https://www.agentready.me/ as the canonical URL.