Agent Request Desk

Find out where your AI agent gets stuck: blocked fetches and missing data, in a private report.

使うべきか

品質と安全性

A
説明の品質
100%
スキーマの完全性
97%
命名の品質
80%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

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

~926トークン数(ツール定義)
~2.4 KB一般的なレスポンスサイズ
注意への影響は中程度(128k コンテキストの 0.72%)

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": {
    "request-desk": {
      "url": "https://agentrequest.dev/mcp"
    }
  }
}

リモートエンドポイント

https://agentrequest.dev/mcpstreamable-http

できること

ツール一覧

ツール(3)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢request_data(description, target, purpose, format, freshness, ...)

Call this when you need specific data for a task and cannot get it: the site returned 403 or 429, showed a CAPTCHA or Cloudflare challenge, sits behind a login wall, has no API, renders only with JavaScript, publishes only as PDF, or the data is spread across many sites or not found at all. Returns pointers to existing sources (official APIs, open datasets, MCP servers) that may already serve the need, plus a log id. Requests are pooled across agents and the most wanted data gets sourced. Free, no key. Do not include personal data about private individuals.

入力スキーマ

{
  "type": "object",
  "properties": {
    "description": {
      "type": "string",
      "minLength": 3,
      "description": "What data you needed, as specifically as possible"
    },
    "target": {
      "description": "Site, organisation or source you tried, if any (domain or name)",
      "type": "string"
    },
    "purpose": {
      "description": "What task the data was for, in a few words",
      "type": "string"
    },
    "format": {
      "description": "Shape you wanted it in, e.g. JSON list, CSV, single value",
      "type": "string"
    },
    "freshness": {
      "description": "How fresh it must be, e.g. real-time, daily, monthly",
      "type": "string"
    },
    "max_price_usd": {
      "description": "Most you (or your operator) would pay per request in USD if this existed, e.g. 0.01",
      "type": "number",
      "minimum": 0
    },
    "agent_name": {
      "description": "Name of your agent or product, optional",
      "type": "string"
    },
    "private": {
      "description": "Set true to have your description, purpose and error text used for matching but not stored",
      "type": "boolean"
    }
  },
  "required": [
    "description"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢request_action(description, target, failure_type, purpose, max_price_usd, ...)

Call this when you tried to do something for your user and could not finish it: there is no API for the action, a CAPTCHA or bot check stopped you, it needs a login or account, it is phone-only or in person only, or a booking or government portal blocks automation. Examples: booking, submitting a form, contacting a business, filing with a portal, sending post. Returns any existing route that already handles it, plus a log id. Requests are pooled and the most requested actions get built. Free, no key.

入力スキーマ

{
  "type": "object",
  "properties": {
    "description": {
      "type": "string",
      "minLength": 3,
      "description": "The action you were trying to take"
    },
    "target": {
      "description": "Service, site or organisation involved",
      "type": "string"
    },
    "failure_type": {
      "description": "Why it failed: no_api, captcha, login_required, bot_blocked, phone_only, human_verification, payment, other",
      "type": "string"
    },
    "purpose": {
      "description": "What the user wanted to achieve",
      "type": "string"
    },
    "max_price_usd": {
      "description": "Most you (or your operator) would pay per request in USD if this existed, e.g. 0.01",
      "type": "number",
      "minimum": 0
    },
    "agent_name": {
      "type": "string"
    },
    "private": {
      "description": "Set true to have your description, purpose and error text used for matching but not stored",
      "type": "boolean"
    }
  },
  "required": [
    "description"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
⚪report_failure(target, failure_type, description, error_message, agent_name, ...)

Call this right after a fetch, scrape or API call fails and stops your task: HTTP 403, HTTP 429, CAPTCHA, Cloudflare challenge, login wall, an empty page that needs JavaScript, PDF-only content, or a page that has gone. Returns an official API or open dataset for the same data where one is known, plus a log id. Does not bypass CAPTCHAs or bot protection. Free, takes seconds.

入力スキーマ

{
  "type": "object",
  "properties": {
    "target": {
      "type": "string",
      "description": "URL or domain that failed"
    },
    "failure_type": {
      "type": "string",
      "description": "e.g. 403, 429, captcha, cloudflare, login_wall, js_render, pdf, timeout"
    },
    "description": {
      "type": "string",
      "minLength": 3,
      "description": "What you were trying to get from it"
    },
    "error_message": {
      "type": "string"
    },
    "agent_name": {
      "type": "string"
    },
    "private": {
      "description": "Set true to have your description, purpose and error text used for matching but not stored",
      "type": "boolean"
    }
  },
  "required": [
    "target",
    "failure_type",
    "description"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 3 件