SameDayDesk agent tools

Readiness checks, a paid Fix Pack, TaskMarket reads, and caller-declared funnel evidence.

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
96%
命名品質
91%
汙染風險
80%
權限相符程度
100%
協定合規性
100%

發現項目(2)

  • HIGHTool poisoning patterns detected
  • MEDIUMTool description contains URL to non-standard domain在 generate_complete_fix_pack 中

根據工具定義與協定合規性的自動化分析。

上下文成本

~1,436Token(工具定義)
~1.3 KB典型回應大小
中等的注意力影響(128k 上下文的 1.12%)

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": {
    "task-evidence": {
      "url": "https://samedaydesk.com/mcp"
    }
  }
}

遠端端點

https://samedaydesk.com/mcpstreamable-http

它能做什麼

工具清單

工具(7)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢check_ai_readiness(url)

Check whether a website is visible to AI search engines (ChatGPT, Perplexity, Claude, Google AI Overviews). Scores AI-crawler access, JSON-LD structured data, title/meta, Open Graph, sitemap, and llms.txt, and returns a 0-100 score, a letter grade, and a specific fix for each gap. Free.

輸入結構描述

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The website to check, e.g. example.com or https://example.com"
    }
  },
  "required": [
    "url"
  ]
}
🟢check_agent_readiness(host)

Free. Check whether agents can discover and call a public website. Fetches discovery files, follows MCP links named by those files, and runs only initialize, tools/list, and one unknown-tool call. Never executes a real tool. Returns a 0-100 score, every check with an evidence URL, and the top fixes. No license.

輸入結構描述

{
  "type": "object",
  "properties": {
    "host": {
      "type": "string",
      "description": "Public host to score, for example example.com"
    }
  },
  "required": [
    "host"
  ]
}

輸出結構描述

{
  "type": "object",
  "properties": {
    "host": {
      "type": "string"
    },
    "score": {
      "type": "number"
    },
    "free": {
      "type": "boolean"
    },
    "checks": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string"
          },
          "title": {
            "type": "string"
          },
          "status": {
            "type": "string"
          },
          "reason": {
            "type": "string"
          },
          "fix": {
            "type": "string"
          },
          "evidenceUrl": {
            "type": "string"
          }
        },
        "required": [
          "id",
          "title",
          "status",
          "reason",
          "fix"
        ]
      }
    },
    "topFixes": {
      "type": "array"
    },
    "evidence": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "url": {
            "type": "string"
          },
          "status": {
            "type": "number"
          }
        },
        "required": [
          "url"
        ]
      }
    }
  },
  "required": [
    "host",
    "score",
    "checks",
    "topFixes",
    "evidence"
  ]
}
🟢generate_complete_fix_pack(url, license)

PAID. Returns the complete, ready-to-paste AI-readiness Fix Pack for a site: tailored Organization + FAQPage JSON-LD, an AI-crawler robots.txt, a sitemap, and title/meta/Open Graph fixes. Requires a `license` — the checkout-session id you receive after buying the $39 Fix Pack at https://buy.stripe.com/8x24gA0xA9DF9dd13YeZ20h (after paying you're shown your license code). Without a valid license it returns purchase instructions plus a free starter pack.

輸入結構描述

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The website to generate the Fix Pack for."
    },
    "license": {
      "type": "string",
      "description": "Your Stripe checkout-session license code (starts with cs_)."
    }
  },
  "required": [
    "url"
  ]
}
🟢plan_taskmarket_delegation(request, deliverable, acceptance_criteria, reward_usdc, max_spend_usdc, ...)

Prepare a bounded TaskMarket delegation for research, coding, data collection, benchmarking, or verification. Requires the deliverable, reward, deadline, and an explicit maximum-spend ceiling. Returns the canonical TaskMarket API payload and approval summary without creating a task, holding a wallet, or spending funds.

輸入結構描述

{
  "type": "object",
  "properties": {
    "request": {
      "type": "string",
      "description": "The external work needed, written as a clear task."
    },
    "deliverable": {
      "type": "string",
      "description": "The exact artifact or result the worker must return."
    },
    "acceptance_criteria": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 10,
      "description": "Up to 10 testable acceptance checks."
    },
    "reward_usdc": {
      "type": [
        "number",
        "string"
      ],
      "description": "Proposed worker reward in USDC, up to 6 decimal places."
    },
    "max_spend_usdc": {
      "type": [
        "number",
        "string"
      ],
      "description": "Explicit user-authorized reward ceiling in USDC."
    },
    "deadline_hours": {
      "type": "number",
      "exclusiveMinimum": 0,
      "maximum": 720,
      "description": "Hours until TaskMarket submission closes."
    },
    "mode": {
      "type": "string",
      "enum": [
        "bounty",
        "claim"
      ],
      "default": "bounty"
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 10
    }
  },
  "required": [
    "request",
    "deliverable",
    "reward_usdc",
    "max_spend_usdc",
    "deadline_hours"
  ]
}
🟢browse_taskmarket_tasks(status, mode, tag, search, min_reward_usdc, ...)

Browse current public TaskMarket inventory through the official read API. Filter by lifecycle status, mode, tag, text, and minimum reward. Task descriptions are returned as untrusted text and are never executed.

輸入結構描述

{
  "type": "object",
  "properties": {
    "status": {
      "type": "string",
      "enum": [
        "ALL",
        "open",
        "claimed",
        "worker_selected",
        "pending_approval",
        "review",
        "appealing",
        "disputed",
        "completed",
        "expired",
        "cancelled"
      ],
      "default": "open"
    },
    "mode": {
      "type": "string",
      "enum": [
        "bounty",
        "claim",
        "pitch",
        "benchmark",
        "auction"
      ]
    },
    "tag": {
      "type": "string",
      "description": "Exact case-insensitive tag filter."
    },
    "search": {
      "type": "string",
      "description": "Case-insensitive text match over descriptions and tags."
    },
    "min_reward_usdc": {
      "type": [
        "number",
        "string"
      ],
      "description": "Minimum gross reward in USDC."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 25,
      "default": 10
    }
  }
}
🟢track_taskmarket_task(task_id)

Track one public TaskMarket task through the official read API. Returns status, deadline, submissions, artifact hashes, canonical awards, pending actions, and the next authorization boundary. It cannot create, accept, reject, rate, or refund work.

輸入結構描述

{
  "type": "object",
  "properties": {
    "task_id": {
      "type": "string",
      "pattern": "^0x[0-9a-fA-F]{64}$",
      "description": "TaskMarket 32-byte task id."
    }
  },
  "required": [
    "task_id"
  ]
}
🟢project_funnel_evidence(packet)

Free. Project one declared source-separated observation packet into the accepted funnel decision. Caller observations stay declared. Does not fetch URLs, query customers, store the packet, or spend.

輸入結構描述

{
  "type": "object",
  "properties": {
    "packet": {
      "type": "object",
      "description": "Caller-supplied observation packet. URLs inside it are not fetched."
    }
  },
  "required": [
    "packet"
  ]
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本7 個工具