Agent Ready
Scan any URL for AI agent readability — Vercel Spec, llmstxt.org, and agent-protocol manifests.
我該用這個嗎
品質與安全性
A
根據工具定義與協定合規性的自動化分析。
上下文成本
~1,964Token（工具定義）
~6.7 KB典型回應大小
中等的注意力影響（128k 上下文的 1.53%）
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"agent-ready-mcp": {
"command": "npx",
"args": [
"agent-ready-mcp"
]
}
}
}可執行的套件
npmagent-ready-mcp
0.7.7stdio遠端端點
https://agent-ready.dev/api/v1/mcpstreamable-http它能做什麼
工具清單
工具（3）
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢scan_site(url, pageLimit)
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.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"maxLength": 2000,
"format": "uri",
"description": "Full URL of the site to scan, e.g. https://example.com. Must be a public http(s) address."
},
"pageLimit": {
"description": "Maximum number of pages to crawl. Defaults to your tier's per-scan page limit when omitted.",
"type": "integer",
"minimum": 1,
"maximum": 2000
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}輸出結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "The scan id."
},
"status": {
"type": "string",
"enum": [
"running",
"completed",
"failed"
],
"description": "Scan status: running, completed, or failed."
},
"shareUrl": {
"description": "Path to the shareable report (/scan/<id>).",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"rootUrl": {
"description": "The scanned site URL.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"vercelScore": {
"description": "Score against the Vercel Agent Readability Spec (0–100); null while running.",
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"vercelRating": {
"description": "Rating band for the Vercel score.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"llmstxtScore": {
"description": "llms.txt score (0–100).",
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"accessibilityScore": {
"description": "Accessibility / layout-stability sub-score (0–100) over the homepage WCAG checks; null when none ran. Separate from the Vercel score.",
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"protocolResults": {
"description": "Agent-protocol checks (C-series) that ran — only for endpoints the site actually exposes.",
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"properties": {
"checkId": {
"type": "string"
},
"name": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"pass",
"fail",
"warn",
"error"
]
},
"message": {
"type": "string"
},
"howToFix": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
}
},
"required": [
"checkId",
"name",
"status",
"message",
"howToFix"
],
"additionalProperties": false
}
},
{
"type": "null"
}
]
},
"accessibilityChecks": {
"description": "Accessibility / layout-stability checks (A-series) run over the homepage.",
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"properties": {
"checkId": {
"type": "string"
},
"name": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"pass",
"fail",
"warn",
"error"
]
},
"message": {
"type": "string"
},
"howToFix": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
}
},
"required": [
"checkId",
"name",
"status",
"message",
"howToFix"
],
"additionalProperties": false
}
},
{
"type": "null"
}
]
},
"pagesScanned": {
"description": "Number of pages scanned.",
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"pagesDiscovered": {
"description": "Number of pages discovered.",
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"pollUrl": {
"description": "Poll URL while the scan is still running.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
}
},
"required": [
"id",
"status"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢get_scan(id)
Fetches a completed or in-progress scan by its id. Only scans owned by the authenticated API key's user are returned.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 1,
"maxLength": 100,
"description": "The scan id returned by scan_site (also the share token in a /scan/<id> URL)."
}
},
"required": [
"id"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}輸出結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "The scan id."
},
"status": {
"type": "string",
"enum": [
"running",
"completed",
"failed"
],
"description": "Scan status: running, completed, or failed."
},
"shareUrl": {
"description": "Path to the shareable report (/scan/<id>).",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"rootUrl": {
"description": "The scanned site URL.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"vercelScore": {
"description": "Score against the Vercel Agent Readability Spec (0–100); null while running.",
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"vercelRating": {
"description": "Rating band for the Vercel score.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"llmstxtScore": {
"description": "llms.txt score (0–100).",
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"accessibilityScore": {
"description": "Accessibility / layout-stability sub-score (0–100) over the homepage WCAG checks; null when none ran. Separate from the Vercel score.",
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"protocolResults": {
"description": "Agent-protocol checks (C-series) that ran — only for endpoints the site actually exposes.",
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"properties": {
"checkId": {
"type": "string"
},
"name": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"pass",
"fail",
"warn",
"error"
]
},
"message": {
"type": "string"
},
"howToFix": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
}
},
"required": [
"checkId",
"name",
"status",
"message",
"howToFix"
],
"additionalProperties": false
}
},
{
"type": "null"
}
]
},
"accessibilityChecks": {
"description": "Accessibility / layout-stability checks (A-series) run over the homepage.",
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"properties": {
"checkId": {
"type": "string"
},
"name": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"pass",
"fail",
"warn",
"error"
]
},
"message": {
"type": "string"
},
"howToFix": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
}
},
"required": [
"checkId",
"name",
"status",
"message",
"howToFix"
],
"additionalProperties": false
}
},
{
"type": "null"
}
]
},
"pagesScanned": {
"description": "Number of pages scanned.",
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"pagesDiscovered": {
"description": "Number of pages discovered.",
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
},
"pollUrl": {
"description": "Poll URL while the scan is still running.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
}
},
"required": [
"id",
"status"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}🟢ask(q, itemType, mode)
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.
輸入結構描述
{
"type": "object",
"properties": {
"q": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "Natural-language question to search Agent Ready's docs, scoring methodology, check registry, and content library (explainers, comparisons, how-to guides, glossary)."
},
"itemType": {
"description": "Restrict results to a content type: methodology, checks, specs, llms-txt, check, page (explainers/guides/glossary), or any (default: all types).",
"type": "string",
"enum": [
"methodology",
"checks",
"specs",
"llms-txt",
"check",
"page",
"any"
]
},
"mode": {
"description": "\"list\" (default) returns matching items; \"summarize\" returns a synthesized answer.",
"type": "string",
"enum": [
"list",
"summarize"
]
}
},
"required": [
"q"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}輸出結構描述
{
"type": "object",
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"description": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
}
},
"additionalProperties": {}
},
"description": "Matching result items (Schema.org-typed)."
},
"message": {
"description": "Extractive summary when mode is 'summarize'.",
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
}
},
"required": [
"results"
],
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false
}社群
證據
近期觀測
已驗證未記錄版本3 個工具
已驗證未記錄版本3 個工具
已驗證未記錄版本3 個工具