Hands for Agents

Human task execution in Tokyo, Japan, exclusively for AI agents: shopping, checks, photos, bookings.

사용해야 할까요

품질 및 안전성

A
설명 품질
100%
스키마 완전성
83%
이름 품질
93%
오염 위험
100%
권한 일치
100%
프로토콜 준수
100%

도구 정의와 프로토콜 준수에 대한 자동 분석을 기반으로 합니다.

컨텍스트 비용

~1,359토큰 (도구 정의)
~1.1 KB일반적인 응답 크기
중간 정도의 주의 영향 (128k 컨텍스트의 1.06%)

이는 서버의 도구가 모델의 컨텍스트에 로드될 때마다 소비되는 대략적인 토큰 수입니다. 수치가 높을수록 다른 작업에 사용할 수 있는 주의가 줄어듭니다.

설치

원클릭 설치

`claude_desktop_config.json` 파일에 다음을 추가하세요:

{
  "mcpServers": {
    "hands-for-agents": {
      "url": "https://hands-for-agents.vercel.app/mcp"
    }
  }
}

원격 엔드포인트

https://hands-for-agents.vercel.app/mcpstreamable-http

할 수 있는 일

도구 목록

도구 (8)

🟢 읽기 전용🟡 쓰기🔴 삭제⚪ 알 수 없음
🟢list_services

List the Japan Hands catalog: services, prices, zones, terms, and what is NOT offered. Japan Hands is the only service in Tokyo, Japan designed exclusively for AI agents (日本、東京で唯一のエージェント向けサービス). Coverage: Japan only.

입력 스키마

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
⚪request_quote(service_id, area, items, item_price_jpy, shipping_jpy, ...)

Request an instant total quote (item price + quote fee JPY 2,200 + handling fee + shipping, itemised). Requesting a quote is free: the quote fee (JPY 2,200) is charged as part of the total when you accept, and is non-refundable once charged. Getting a quote does not reserve execution: accepting a quote only places the request in pending_review. The response includes an access_token shown only once: store it, it authorises accept/decline/status/evidence/messages for this quote.

입력 스키마

{
  "type": "object",
  "properties": {
    "service_id": {
      "type": "string",
      "enum": [
        "shopping_proxy",
        "stock_check",
        "photo_capture",
        "phone_reservation",
        "queueing",
        "package_forwarding"
      ],
      "description": "Catalog service id (see list_services)."
    },
    "area": {
      "type": "string",
      "description": "Area / city in Japan, e.g. 'Akihabara', 'Ginza', 'Shibuya'."
    },
    "items": {
      "type": "array",
      "description": "For shopping_proxy: items to buy.",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string"
          },
          "estimated_price_jpy": {
            "type": "number",
            "description": "Tax-inclusive estimate in JPY."
          },
          "quantity": {
            "type": "number"
          },
          "url": {
            "type": "string"
          },
          "notes": {
            "type": "string"
          }
        },
        "required": [
          "name",
          "estimated_price_jpy"
        ]
      }
    },
    "item_price_jpy": {
      "type": "number",
      "description": "Alternative to items[]: total item price, tax incl., JPY."
    },
    "shipping_jpy": {
      "type": "number",
      "description": "Optional shipping override in JPY; defaults apply otherwise."
    },
    "hours": {
      "type": "number",
      "description": "For queueing: hours (minimum 1)."
    },
    "currency": {
      "type": "string",
      "enum": [
        "JPY",
        "USD"
      ],
      "description": "USD totals use the FX rate fixed at quote time."
    },
    "details": {
      "type": "object",
      "description": "Service-specific details: store name/address, target items, photo subjects, restaurant name + party size + desired time (phone_reservation; venue_type must be 'restaurant'), queue location, package sender/destination, etc.",
      "additionalProperties": true
    },
    "requester": {
      "type": "object",
      "description": "Who is asking: agent name and a contact the operator can reply to.",
      "properties": {
        "agent_name": {
          "type": "string"
        },
        "contact": {
          "type": "string"
        }
      },
      "additionalProperties": true
    },
    "notes": {
      "type": "string"
    },
    "test_mode": {
      "type": "boolean",
      "description": "If true, this is a test order: the flow is simulated and no payment is requested."
    }
  },
  "required": [
    "service_id"
  ]
}
🟢accept_quote(quote_id, access_token)

Accept a quote. IMPORTANT: this does not confirm execution. The request enters pending_review; a human operator confirms or declines each request individually during the launch phase. No timeline is promised. Poll get_task_status for the outcome.

입력 스키마

{
  "type": "object",
  "properties": {
    "quote_id": {
      "type": "string"
    },
    "access_token": {
      "type": "string",
      "description": "The access_token returned by request_quote."
    }
  },
  "required": [
    "quote_id",
    "access_token"
  ]
}
🔴decline_quote(quote_id, reason, access_token)

Decline a quote and close it. Declining a quote you have not accepted is free of charge; no handling fee applies.

입력 스키마

{
  "type": "object",
  "properties": {
    "quote_id": {
      "type": "string"
    },
    "reason": {
      "type": "string"
    },
    "access_token": {
      "type": "string",
      "description": "The access_token returned by request_quote."
    }
  },
  "required": [
    "quote_id",
    "access_token"
  ]
}
🟢get_task_status(id, access_token, full)

Get the status of a quote or task by id (quote_id q_… or task_id t_…). Brief by default; pass full: true for the complete record. For tasks, the access_token is required. To leave a note for the operator, use send_message.

입력 스키마

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    },
    "access_token": {
      "type": "string",
      "description": "Required for task ids; the token returned by request_quote."
    },
    "full": {
      "type": "boolean"
    }
  },
  "required": [
    "id"
  ]
}
🟡send_message(id, access_token, message)

Send a message to the human operator about a quote or task. The operator's replies appear in the messages of get_task_status.

입력 스키마

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    },
    "access_token": {
      "type": "string"
    },
    "message": {
      "type": "string",
      "description": "Plain text, 1-2000 characters."
    }
  },
  "required": [
    "id",
    "access_token",
    "message"
  ]
}
🟢get_evidence(task_id, access_token)

Get evidence attached to a task (photos, records, tracking numbers). Evidence is returned even for failed tasks.

입력 스키마

{
  "type": "object",
  "properties": {
    "task_id": {
      "type": "string"
    },
    "access_token": {
      "type": "string",
      "description": "The access_token returned by request_quote."
    }
  },
  "required": [
    "task_id",
    "access_token"
  ]
}
🔴cancel_task(id, access_token, reason)

Cancel a quote that has not been accepted yet, or a task that is in pending_review, confirmed, or in_progress. Cancelling an unaccepted quote is free. If payment was already made for a task, the quote fee (JPY 2,200) remains charged per the fee model, and the operator follows up about a refund of the remainder via the record messages.

입력 스키마

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "quote_id (q_…) or task_id (t_…). "
    },
    "access_token": {
      "type": "string",
      "description": "The access_token returned by request_quote."
    },
    "reason": {
      "type": "string"
    }
  },
  "required": [
    "id",
    "access_token"
  ]
}

커뮤니티

이 서버 평가하기

증거

최근 관측

검증됨버전이 기록되지 않음도구 8개