# Agent Ready

Scan any public URL for AI agent readability and get back a 0–100 score plus per-check remediation hints. The same engine that powers [agent-ready.dev](https://agent-ready.dev), packaged as an MCP se…

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y smithery mcp add agent-ready/agent-ready-mcp

# Browse available tools
npx -y smithery tool list agent-ready/agent-ready-mcp

# Get full schema for a tool
npx -y smithery tool get agent-ready/agent-ready-mcp scan_site

# Call a tool
npx -y smithery tool call agent-ready/agent-ready-mcp scan_site '{}'
```

## Tools (2)

- `scan_site` — Runs the agent-ready.dev scanner against a URL and returns structured results: a 0–100 Vercel agent-readability score, …
- `get_scan` — Fetches a completed or in-progress scan by its 10-character id. Returns the same scan object shape as scan_site when co…

```bash
# Get full input/output schema for a tool
npx -y smithery tool get agent-ready/agent-ready-mcp <tool-name>
```

## Resources

- `agent-ready://methodology` — How Agent Ready computes the 0–100 readability score and the llms.txt sub-score. Covers the 59 checks across four categ…
- `agent-ready://checks` — Reference table of all 59 checks Agent Ready runs, grouped by category (site, page, llms.txt, protocol). Each row pairs…
- `agent-ready://llms.txt` — The /llms.txt file agent-ready.dev publishes for AI agents discovering it as a tool. Useful as a worked example for the…
- `agent-ready://specs` — Canonical URLs and check-ID mappings for the seven specifications Agent Ready implements: Vercel Agent Readability Spec…

## Prompts (3)

- `scan` (url) — Run a fresh agent-readability scan against a URL and summarise the most important findings.
- `interpret_scan` (id) — Fetch a previous scan by id and translate the per-check findings into plain-English explanations.
- `remediation_plan` (id, focus) — Fetch a scan by id and produce a prioritised, actionable remediation plan, optionally focused on SEO or agent-protocol …