DeveloperVerified

Agent Ready WebMCP tools

Score any website against the Vercel Agent Readability Spec and llmstxt.org standard. Get actionable fixes to make your site AI-agent friendly.

3 tools1 ways to use

What an agent can do on Agent Ready

Score any website against the Vercel Agent Readability Spec and llmstxt.org standard. Get actionable fixes to make your site AI-agent friendly. This page documents every listed tool: what it does, how to install it, and the input fields an agent should send.

WebMCP tools on Agent Ready

Get data

scan_site

Read the full scan_site page

Scan a public website for AI agent-readability against the Vercel Agent Readability Spec, llmstxt.org, and agent-protocol manifests. Returns a 0–100 score, the llms.txt score, and the top failing checks with a link to the full per-check report.

How to install

Open the agent-ready.dev website and ask your browser agent to use scan_site

Install browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.

Run with an agent

Use the scan_site tool on agent-ready.dev with url: <string>. Return the structured result and cite the source page.

Input contract

url string The public URL to scan, e.g. the linked page

Open the source definition

Get data

get_scan

Read the full get_scan page

Fetch a previously run Agent Ready scan by its id (shareToken) and return the score summary. Use to re-read a result or poll a scan that was still running.

How to install

Open the agent-ready.dev website and ask your browser agent to use get_scan

Install browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.

Run with an agent

Use the get_scan tool on agent-ready.dev with id: <string>. Return the structured result and cite the source page.

Input contract

id string The scan id / shareToken.

Open the source definition

Search & find

ask

Read the full ask page

Natural-language search (NLWeb /ask) over Agent Ready's own content — scoring methodology, the check registry, the specs it validates, and the content library (explainers, comparisons, how-to guides, glossary). Returns Schema.org-typed results. Optional itemType narrows the corpus; mode 'summarize' adds an extractive summary.

How to install

Open the agent-ready.dev website and ask your browser agent to use ask

Install browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.

Run with an agent

Use the ask tool on agent-ready.dev with q: <string>, itemType: <string>, mode: <string>. Return the structured result and cite the source page.

Input contract

q string The natural-language question.
itemType string Narrow the search to one corpus type (default: any).
mode string list (default) or summarize for an extractive summary.

Open the source definition