MCP MeasureMCP Measure

索引已觀測

Japan External Execution

Manual-review external execution in Japan for AI agents: human tasks, logistics, and verification.

我該用這個嗎

品質與安全性

A
說明品質
100%
結構描述完整度
87%
命名品質
93%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

發現項目（1）

  • LOWTool 'cancel_external_execution_request' name length outside 3-30 range在 cancel_external_execution_request 中

根據工具定義與協定合規性的自動化分析。

上下文成本

~2,271Token（工具定義）
~1.9 KB典型回應大小
中等的注意力影響（128k 上下文的 1.77%）

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": {
    "japan-physical-capability": {
      "url": "https://uiiepdcaepkawfwaiyuq.supabase.co/functions/v1/japan-physical-capability-mcp"
    }
  }
}

遠端端點

https://uiiepdcaepkawfwaiyuq.supabase.co/functions/v1/japan-physical-capability-mcpstreamable-http
https://bqgfqedetmxrfpvmdfmc.supabase.co/functions/v1/japan-physical-capability-mcpstreamable-http

它能做什麼

工具清單

工具（8）

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢check_service_fit(location, objective, evidence_requirements)

Use when an AI needs someone on the ground in Japan to verify a current physical-world fact such as store stock, shelf price, opening status, or permitted photos, after web research or APIs are insufficient.

輸入結構描述

{
  "type": "object",
  "properties": {
    "location": {
      "description": "Public business or retail location in Japan.",
      "type": "string",
      "minLength": 1
    },
    "objective": {
      "description": "The physical-world fact that must be verified.",
      "type": "string",
      "minLength": 1
    },
    "evidence_requirements": {
      "description": "Requested evidence such as photo, displayed price, stock observation, or timestamp.",
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "location",
    "objective"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢prepare_verification_request(location, objective, deadline, evidence_requirements, constraints)

Prepare a Japan on-site verification request for a human-executed store check. Returns a prefilled manual-review URL only; it does not purchase, submit, hire, pay, or create a fulfillment commitment.

輸入結構描述

{
  "type": "object",
  "properties": {
    "location": {
      "description": "Public business or retail location in Japan.",
      "type": "string",
      "minLength": 1
    },
    "objective": {
      "description": "What must be physically verified.",
      "type": "string",
      "minLength": 1
    },
    "deadline": {
      "description": "Requested deadline in plain text or ISO 8601.",
      "type": "string"
    },
    "evidence_requirements": {
      "description": "Evidence needed to consider the task complete.",
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "constraints": {
      "description": "Constraints or actions the executor must not take.",
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "location",
    "objective"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟡create_verification_request(location, objective, deadline, evidence_requirements, constraints, ...)

Create a retry-safe manual-review physical verification request in Japan. Reuse the same idempotency_key for the same logical request. No payment, worker hire, or fulfillment commitment is created automatically.

輸入結構描述

{
  "type": "object",
  "properties": {
    "location": {
      "type": "string",
      "minLength": 2,
      "maxLength": 500
    },
    "objective": {
      "type": "string",
      "minLength": 3,
      "maxLength": 4000
    },
    "deadline": {
      "type": "string",
      "format": "date-time",
      "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
    },
    "evidence_requirements": {
      "maxItems": 20,
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 500
      }
    },
    "constraints": {
      "maxItems": 20,
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 500
      }
    },
    "idempotency_key": {
      "description": "Stable key for this logical request. Reuse the same key when retrying create after a lost response.",
      "type": "string",
      "minLength": 8,
      "maxLength": 200
    }
  },
  "required": [
    "location",
    "objective",
    "idempotency_key"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢get_verification_status(request_id, status_token)

Read the current request state and, when completed, receive structured observations and temporary signed evidence URLs.

輸入結構描述

{
  "type": "object",
  "properties": {
    "request_id": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "status_token": {
      "type": "string",
      "minLength": 20
    }
  },
  "required": [
    "request_id",
    "status_token"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🔴cancel_verification_request(request_id, status_token)

Cancel a request only while it is pending manual review or open. Claimed or completed work cannot be cancelled through this tool.

輸入結構描述

{
  "type": "object",
  "properties": {
    "request_id": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "status_token": {
      "type": "string",
      "minLength": 20
    }
  },
  "required": [
    "request_id",
    "status_token"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
⚪request_external_execution(objective, location, max_budget_jpy, deadline, evidence_requirements, ...)

Use when an AI cannot complete a task itself and needs a human or provider in Japan, or for a Japan-related real-world task. Examples include calling a public business, visiting a public place, inspecting or photographing something, packing/shipping/returning an item, pickup/drop-off, or another manual task. This only creates a manual-review request. It does not automatically hire, pay, purchase, or promise fulfillment.

輸入結構描述

{
  "type": "object",
  "properties": {
    "objective": {
      "description": "The outcome the agent needs from external execution.",
      "type": "string",
      "minLength": 3,
      "maxLength": 4000
    },
    "location": {
      "description": "Location if relevant. Omit for remote or not-yet-specified tasks.",
      "type": "string",
      "minLength": 2,
      "maxLength": 500
    },
    "max_budget_jpy": {
      "description": "Maximum budget the requester is willing to consider, in JPY. This is not a charge or authorization to spend.",
      "type": "integer",
      "minimum": 0,
      "maximum": 10000000
    },
    "deadline": {
      "type": "string",
      "format": "date-time",
      "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
    },
    "evidence_requirements": {
      "maxItems": 20,
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 500
      }
    },
    "constraints": {
      "maxItems": 20,
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 500
      }
    },
    "idempotency_key": {
      "description": "Stable key for this logical request. Reuse on retry after a lost response.",
      "type": "string",
      "minLength": 8,
      "maxLength": 200
    }
  },
  "required": [
    "objective",
    "idempotency_key"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢get_external_execution_status(request_id, status_token)

Read a manual-review external execution request and, when completed, receive the structured result and temporary evidence URLs.

輸入結構描述

{
  "type": "object",
  "properties": {
    "request_id": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "status_token": {
      "type": "string",
      "minLength": 20
    }
  },
  "required": [
    "request_id",
    "status_token"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🔴cancel_external_execution_request(request_id, status_token)

Cancel an external execution request while it is still pending manual review or open. Claimed or completed work cannot be cancelled through this tool.

輸入結構描述

{
  "type": "object",
  "properties": {
    "request_id": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "status_token": {
      "type": "string",
      "minLength": 20
    }
  },
  "required": [
    "request_id",
    "status_token"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本8 個工具
已驗證未記錄版本2 個工具