Agent Ready MCP Server

@mlava

リポジトリ

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

作者

mlava

投稿者

Mark Lavercombe

Agent Ready MCP Server 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

Agent Ready MCP Server の設定

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>"
      }
    }
  }
}

Agent Ready MCP Server のツール

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. Works without an API key on the anonymous free tier (3 scans/30 days per IP, 25-page depth, synchronous). With a Pro AGENT_READY_API_KEY it scans deeper (up to 250 pages) and 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. Requires a Pro API key — scan history is account-scoped. (Anonymous scan_site calls return their result inline, so keyless use never needs this tool.)

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). Public, no API key required. Returns Schema.org-typed result objects; optional itemType narrows to a corpus type and mode 'summarize' adds an extractive summary.

Validates a page's (or a pasted) JSON-LD against Agent Ready's structured-data checks (schema lint + agent-coherence: freshness honesty, canonical/.md coherence, entity-name consistency, extraction signal) and returns a verdict with per-check fix guidance. Provide exactly one of `url` (fetch + validate) or `jsonld` (validate a string the agent just authored — no network needed). Public, no API key required. The one structured-data check the first-party validators (validator.schema.org, Rich Results Test) don't do.

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.

よくある質問

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

Legion MCP

faulkj

MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.

Rokha

Rokha AI LLC

Search a registry of agent skills and MCP servers, run them for real (sandbox or remote MCP, no install, a trace on every run), and hire proven agents for USDC.

xhostd

Agent-first hosting. From Claude, Cursor, or Codex, your agent can create an app, push code, and deploy it to a live HTTPS URL, with managed Postgres, custom domains, environment variables, backups, and rollback.

Nero AI Image Processing

nero-com

We provide AI-powered tools for image enhancement, upscaling, background removal, photo restoration, colorization, denoising, and compression. All features are available through our API documentation.

TruVerifAI Panel-review

TruVerifAI

TruVerifAI's Panel Review is the guardian agent for AI's highest-stakes coding decisions: four frontier models argue over an AI coding agent's riskiest designs, diffs, and commits before they execute, with local review g