Agent Ready

Name: Agent Ready
Author: mlava

@mlava

Agent Ready について

AI agent readability scanner — score any public URL against the Vercel Agent Readability Spec, llmstxt.org, and 6 agent-protocol manifests (MCP, A2A, agents.json, agent-permissions, UCP, x402). 59 checks with per-check fix guidance. Same engine as agent-ready.dev.

#developer-tools #seo #ai-search #llms-txt #agents-md #agent-readability #scanner #validator #vercel-spec #mcp-server-card #a2a #agents-json #agent-permissions #ucp #x402 #claude #anthropic

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

公開者

mlava

投稿者

Mark Lavercombe

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "agent-ready": {
      "command": "npx",
      "args": [
        "-y",
        "agent-ready-mcp@latest"
      ],
      "env": {
        "AGENT_READY_API_KEY": "<YOUR_AGENT_READY_API_KEY>"
      }
    }
  }
}

ツール

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; if the local poll deadline elapses, the tool returns the scan id and asks you to poll with get_scan.

Fetches a completed or in-progress scan by its id. Only scans owned by the authenticated API key's user are returned.

概要

What is Agent Ready?

Agent Ready is an AI agent readability scanner that takes any public URL and returns a 0–100 score with per-check remediation hints. It wraps the same engine powering agent-ready.dev and lets Claude Desktop, Claude Code, Cursor, Cline, VS Code, and Windsurf run scans inline and explain results.

How to use Agent Ready?

Configure the MCP server in your client’s mcpServers setting using npx -y agent-ready-mcp@latest and set the AGENT_READY_API_KEY environment variable (Pro or Team tier required). Once connected, use the scan_site tool to run a fresh scan or get_scan to fetch a previous scan by id. Prompts like scan, interpret_scan, and remediation_plan provide plain‑English summaries and prioritized fix documentation.

Key features of Agent Ready

59 checks across 4 spec families (Vercel, llmstxt, agent‑protocol manifests).
Every failing check includes a concrete howToFix string.
Two tools: scan_site (fresh scan) and get_scan (retrieve by id).
Three prompts: scan, interpret_scan, and remediation_plan.
Ships a Claude Skill descriptor for activation routing.
Runs via npm, hosted HTTP, or on Smithery.

Use cases of Agent Ready

Evaluate your own site’s agent readability before deploying.
Review a competitor’s public URL for missing llms.txt or agent manifests.
Integrate inline scans into Claude Desktop or Cursor to get remediation hints.
Generate a prioritized fix plan focused on SEO or agent‑specific issues.
Validate that a URL satisfies the Vercel Agent Readability Spec.

FAQ from Agent Ready

What API key do I need?

Issue a Pro API key from the dashboard at agent-ready.dev/dashboard/api-keys. The MCP server requires a Pro or Team tier subscription; free‑tier scans are available through the web UI only.

What transports does Agent Ready support?

The MCP server can be run locally via npx (stdio transport) or as a hosted Streamable HTTP endpoint at https://agent-ready.dev/api/v1/mcp (Bearer authentication).

How is Agent Ready different from the web UI?

The MCP server provides programmatic access from AI clients (Claude Desktop, Cursor, etc.) and includes prompts for interpretation and remediation. The web UI offers free‑tier scans.

Does Agent Ready require an internet connection?

Yes, the server must reach agent-ready.dev to run scans. Scans are performed against public URLs you provide.

What are the 59 checks divided into?

38 checks against the Vercel Agent Readability Spec, 10 against the llmstxt.org specification, and 11 against agent‑protocol manifests (MCP Server Cards, A2A Agent Cards, agents.json, agent-permissions.json, UCP, x402 Payment Required).

「AI とエージェント」の他のコンテンツ

Sequential Thinking Multi-Agent System (MAS)

FradSer

An advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.

306

欢迎来到智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797