Toolcard

Cited checks for one MCP tool or a tools list, plus a called-or-ignored tally.

我该使用它吗

质量与安全性

A
描述质量
95%
模式完整度
80%
命名质量
90%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~571token 数(工具定义)
~902 B典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.45%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "toolcard": {
      "url": "https://agentghostedme.com/mcp"
    }
  }
}

远程端点

https://agentghostedme.com/mcpstreamable-http

它能做什么

工具清单

工具(4)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢check_tool(name, description, inputSchema)

Check one MCP tool name, description, and input schema against Toolcard cited rules. Returns findings. A finding with an answer page includes resource, a toolcard://answers URI to pass to resources/read. Does not store the tool.

输入模式

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Tool name, for example manage_user"
    },
    "description": {
      "type": "string",
      "description": "Description shown to the model"
    },
    "inputSchema": {
      "type": "object",
      "description": "JSON Schema object for the tool arguments"
    }
  },
  "required": [
    "name"
  ]
}
🟢check_server(tools, result)

Check every tool in a tools/list result or a server card. Returns per-tool findings plus duplicate-name, overlapping-descriptions, and too-many-tools. Those three omit resource. Does not store the tools.

输入模式

{
  "type": "object",
  "properties": {
    "tools": {
      "type": "array",
      "description": "Tools from a tools/list result or a server card. Each item has name, description, and inputSchema.",
      "items": {
        "type": "object"
      }
    },
    "result": {
      "type": "object",
      "description": "JSON-RPC tools/list result. Used only when tools is omitted. The array is result.tools."
    }
  }
}
⚪report_outcome(name, result, description, client, report_id)

Record whether an agent called or ignored a tool. Stores the name, a SHA-256 of the description, and the result. Does not store the raw description.

输入模式

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Tool name that was offered to the agent"
    },
    "result": {
      "type": "string",
      "enum": [
        "called",
        "ignored"
      ],
      "description": "Whether an agent called the tool"
    },
    "description": {
      "type": "string",
      "description": "Hashed with SHA-256 and not stored"
    },
    "client": {
      "type": "string",
      "description": "Optional short label such as cursor. No account ids."
    },
    "report_id": {
      "type": "string",
      "description": "Optional idempotency key, 8 to 80 letters, digits, underscore or hyphen"
    }
  },
  "required": [
    "name",
    "result"
  ]
}
🟢outcome_summary

Return the anonymous tally of called versus ignored reports on this server. Not a representative sample.

输入模式

{
  "type": "object",
  "properties": {}
}

社区

评价此服务器

证据

最近观测

已验证未记录版本4 个工具