agentready
Scan any public site for AI-agent visibility; get scored findings, a machine-readable fix pack, and
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
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": {
"agentready": {
"url": "https://www.agentready.me/api/mcp"
}
}
}遠端端點
https://www.agentready.me/api/mcpstreamable-http它能做什麼
工具清單
工具（7）
⚪scan_url(url, publish_report)
Run an AgentReady scan of a public URL. Returns the 0-100 score, per-phase findings, top priorities, and the Fix Pack v2 implementation contract. Repository paths remain candidate targets until a connected-repository resolver proves them.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Public site URL (https://example.com)"
},
"publish_report": {
"type": "boolean",
"description": "Create an unlisted, expiring public report link. Defaults to false."
}
},
"required": [
"url"
]
}🟢get_fix_pack(url)
Scan a public URL and return Fix Pack v2: prioritized fixes with stable ids, observed evidence, candidate target URLs and repository paths, review gates, and fix-specific acceptance assertions for a coding agent.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Public site URL (https://example.com)"
}
},
"required": [
"url"
]
}⚪verify_fixes(url, previous_fix_pack)
Re-scan a public URL and evaluate fix-specific stable ids from a previous v1 or v2 Fix Pack. A fix closes when its finding id is absent; score delta is secondary evidence only.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Public site URL (https://example.com)"
},
"previous_fix_pack": {
"type": "object",
"description": "The Fix Pack returned earlier by get_fix_pack (or an object with {score, fixes:[{id}]})."
}
},
"required": [
"url",
"previous_fix_pack"
]
}🟢get_public_report(report_id, history)
Read the latest saved public scan report or bounded history using its opaque report id. Reports are only created after explicit opt-in and expire after 30 days.
輸入結構描述
{
"type": "object",
"properties": {
"report_id": {
"type": "string",
"description": "Opaque report id returned by scan_url when publish_report is true."
},
"history": {
"type": "boolean",
"description": "Return saved snapshots newest first instead of only the latest snapshot."
}
},
"required": [
"report_id"
]
}🟢check_crawler_access(url)
Fetch robots.txt and a bounded public page through validated redirects, then inspect named-token path rules, final delivery, X-Robots-Tag, and HTML meta robots. Named-bot edge/WAF treatment remains unobservable.
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Public site URL and path to evaluate (https://example.com/docs)"
}
},
"required": [
"url"
]
}🟢audit_openapi_readiness(document)
Statically inspect an OpenAPI 3.0 or 3.1 JSON object or JSON string for operation identity, auth and scopes, errors, examples, retries, limits, lifecycle, pagination, and workflows. No API operation is executed.
輸入結構描述
{
"type": "object",
"properties": {
"document": {
"description": "OpenAPI JSON object or a string containing JSON. YAML is reported as unsupported and unobservable.",
"oneOf": [
{
"type": "object"
},
{
"type": "string"
}
]
}
},
"required": [
"document"
]
}⚪validate_a2a_agent_card(card)
Statically validate an A2A Agent Card JSON object. Strict-current evidence and legacy interoperability are reported separately; no agent endpoint or skill is invoked.
輸入結構描述
{
"type": "object",
"properties": {
"card": {
"type": "object",
"description": "A2A Agent Card JSON object."
}
},
"required": [
"card"
]
}社群
證據