Readiness scorer — can an agent sign up to your SaaS?
Probe a signup URL you own and score whether an AI agent can sign up unaided.
使うべきか
品質と安全性
検出事項（1）
- LOWTool 'readiness_get_verification_token' name length outside 3-30 rangereadiness_get_verification_token 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"readiness-scorer": {
"url": "https://agentwares-readiness.vercel.app/api/mcp"
}
}
}リモートエンドポイント
https://agentwares-readiness.vercel.app/api/mcpstreamable-httpできること
ツール一覧
ツール（3）
🟢readiness_get_verification_token(url)
Step 1 of a readiness scan. Returns the domain-ownership token for the URL's host plus the three ways to publish it (DNS TXT record, <meta> tag, /.well-known file). The token is deterministic for the host, so calling this again returns the same value. Nothing is stored.
入力スキーマ
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public https URL of the SaaS signup (or landing) page, e.g. https://example.com/signup"
}
},
"required": [
"url"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢readiness_request_scan(url)
Step 2. Verifies domain ownership (DNS TXT / meta tag / .well-known must carry the token from readiness_get_verification_token), then queues a Playwright probe that tries to sign up, accept the terms and mint an API key with no human. Returns the scan id and the public results URL. Fails with DOMAIN_NOT_VERIFIED (with instructions) or RATE_LIMITED (3 scans per host per day). Never solves CAPTCHAs.
入力スキーマ
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public https URL of the SaaS signup (or landing) page, e.g. https://example.com/signup"
}
},
"required": [
"url"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢readiness_get_scan(id)
Step 3. Poll a scan by id. While status is queued/running only metadata is returned; when done you get the 0-100 score, grade, per-item rubric points with evidence, the fix list, and what could not be observed.
入力スキーマ
{
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 8,
"maxLength": 64,
"description": "scan id returned by readiness_request_scan"
}
},
"required": [
"id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}コミュニティ
エビデンス