mcp-my-site

Search and fetch tools for one website, served from an index you build with the mcpmysite crawler.

我该使用它吗

质量与安全性

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

发现(3)

  • HIGHTool poisoning patterns detected
  • MEDIUMTool description contains URL to non-standard domain在 search 中
  • LOWTool 'fetch' suggests web access but openWorldHint=false在 fetch 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~505token 数(工具定义)
~1.9 KB典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.39%)

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": {
    "mcp-my-site": {
      "url": "https://ai.pournasserian.com/mcp"
    }
  }
}

远程端点

https://ai.pournasserian.com/mcpstreamable-http

它能做什么

工具清单

工具(2)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢search(query, limit)

Searches the website Amir Pournasserian (https://pournasserian.com/): Serial entrepreneur and hands-on AI architect. I build AI and platform systems that have to keep working once they meet production, compliance and scale. Hybrid keyword and semantic search over its 52 pages; returns the best matching pages with a short snippet each. Call fetch with a result's id or URL to read the whole page.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "description": "What to look for. Natural language or keywords.",
      "type": "string"
    },
    "limit": {
      "description": "Maximum number of pages to return, 1 to 20. Default 10.",
      "type": "integer",
      "default": 10
    }
  },
  "required": [
    "query"
  ]
}

输出模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string"
    },
    "keywordOnly": {
      "type": "boolean"
    },
    "results": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string"
          },
          "title": {
            "type": "string"
          },
          "url": {
            "type": "string"
          },
          "snippet": {
            "type": "string"
          },
          "section": {
            "type": [
              "string",
              "null"
            ]
          },
          "score": {
            "type": "number"
          }
        },
        "required": [
          "id",
          "title",
          "url",
          "snippet",
          "section",
          "score"
        ]
      }
    }
  },
  "required": [
    "query",
    "keywordOnly",
    "results"
  ]
}
🟢fetch(id, url)

Returns the full content of one page of the website as Markdown in text, with its title, description, language and last modified date. Pass the id (or url) of a search result.

输入模式

{
  "type": "object",
  "properties": {
    "id": {
      "description": "The id of a search result.",
      "type": [
        "string",
        "null"
      ],
      "default": null
    },
    "url": {
      "description": "Absolute URL of the page. An alternative to id; pass either one.",
      "type": [
        "string",
        "null"
      ],
      "default": null
    }
  }
}

输出模式

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    },
    "url": {
      "type": "string"
    },
    "title": {
      "type": "string"
    },
    "text": {
      "type": "string"
    },
    "description": {
      "type": [
        "string",
        "null"
      ]
    },
    "language": {
      "type": "string"
    },
    "modified": {
      "type": [
        "string",
        "null"
      ],
      "format": "date-time"
    }
  },
  "required": [
    "id",
    "url",
    "title",
    "text",
    "description",
    "language",
    "modified"
  ]
}

社区

评价此服务器

证据

最近观测

已验证未记录版本2 个工具