# Agent Ready MCP server

Scan any URL for AI agent readability — Vercel Spec, llmstxt.org, and agent-protocol manifests.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-mlava-agent-ready-mcp
- Repository: https://github.com/mlava/agent-ready-mcp
- Website: https://agent-ready.dev

## Install
- Command: `npx -y agent-ready-mcp`
- Endpoint: https://agent-ready.dev/api/v1/mcp
- Auth: Not captured

## Setup notes
- Package: Npm agent-ready-mcp v0.7.2
- Environment variable: AGENT_READY_API_KEY (secret)
- Remote endpoint: https://agent-ready.dev/api/v1/mcp

## Tools
- scan_site (Scan a site for AI agent readability) - Runs the agent-ready.dev scanner against a URL and returns structured results: Vercel score, llmstxt.org score, and per-check findings with remediation hints. Scans may take up to ~60s; for larger scans the tool returns a scan id and asks you to poll with get_scan. Endpoint: https://agent-ready.dev/api/v1/mcp
- get_scan (Get a previous scan by id) - Fetches a completed or in-progress scan by its id. Only scans owned by the authenticated API key's user are returned. Endpoint: https://agent-ready.dev/api/v1/mcp
- ask (Ask Agent Ready in natural language) - 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 result objects. Optional itemType narrows to a corpus type; mode 'summarize' adds an extractive summary. Endpoint: https://agent-ready.dev/api/v1/mcp

## Resources
- ui://widget/agent-ready-score.html - Agent Ready score Interactive AI agent-readability score card and per-check breakdown for a scanned site. MIME type: text/html;profile=mcp-app
- agent-ready://methodology - Scoring methodology How Agent Ready computes the 0–100 readability score and the llms.txt sub-score. Covers the 70 checks across four categories, rating bands, weighting, and JS-rendering handling. MIME type: text/markdown
- agent-ready://checks - Check registry Reference table of all 70 checks Agent Ready runs, grouped by category (site, page, llms.txt, protocol, accessibility). Each row pairs the stable check ID (e.g. P11, S15, L9, C3) with its human-readable name. Use this to identify a check by id when interpreting scan results. MIME type: text/markdown
- agent-ready://llms.txt - Agent Ready's own llms.txt The /llms.txt file agent-ready.dev publishes for AI agents discovering it as a tool. Mirrors the live document at https://agent-ready.dev/llms.txt. Useful as a worked example for the llms.txt validator and for clients introspecting Agent Ready's surface. MIME type: text/markdown
- agent-ready://specs - Specifications Agent Ready validates against Canonical URLs and check-ID mappings for the specifications Agent Ready implements: Vercel Agent Readability Spec, llmstxt.org, MCP Server Cards (SEP-1649 / RFC 9728), A2A Agent Cards (a2a.proto v1.0.0), Wildcard agents.json, agent-permissions.json, UCP (RFC 8414), x402 and MPP payments, NLWeb, API Catalog (RFC 9727), Web Bot Auth, Agent Skills Discovery, content parity, and Agent-driven UI (A2UI). MIME type: text/markdown

## Prompts
- scan - Scan a site for AI agent readability Run a fresh agent-readability scan against a URL and summarise the most important findings. Arguments: url
- interpret_scan - Explain a previous scan in plain English Fetch a previous scan by id and translate the per-check findings into plain-English explanations. Arguments: id
- remediation_plan - Produce a prioritised fix-it plan for a scan Fetch a scan by id and produce a prioritised, actionable remediation plan, optionally focused on SEO or agent-protocol fixes. Arguments: id, focus

## Metadata
- Owner: io.github.mlava
- Version: 0.7.2
- Runtime: Npm
- Transports: STDIO, HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 31, 2026
- Source: https://registry.modelcontextprotocol.io