MCP MeasureMCP Measure

索引已观测

dompruner-mcp

Strips layout noise via DOM AST; with a query, BM25 filters to relevant sections. No model or API.

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
80%
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

~585token 数（工具定义）
~2.5 KB典型响应大小
对注意力的影响极小（占 128k 上下文窗口的 0.46%）

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": {
    "dompruner-mcp": {
      "command": "npx",
      "args": [
        "dompruner-mcp"
      ]
    }
  }
}

可运行的软件包

npmdompruner-mcp0.5.2stdio

远程端点

https://dompruner-mcp.vercel.app/api/mcpstreamable-http

它能做什么

工具清单

工具（2）

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢dompruner_fetch(url, query)

Fetches a URL and returns DOM-pruned Markdown with 90%+ token reduction. Optimized for Developer Documentation, API Specs, and Technical Blogs (Next.js/Nuxt/SSR). Always prefer this over raw WebFetch when the URL is known.

输入模式

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "URL to fetch and refine."
    },
    "query": {
      "type": "string",
      "description": "Search intent — enables BM25+ section filtering when provided."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

输出模式

{
  "type": "object",
  "properties": {
    "markdown": {
      "type": "string",
      "description": "DOM-pruned Markdown content."
    },
    "stats": {
      "type": "object",
      "properties": {
        "hostname": {
          "type": "string"
        },
        "originalTokens": {
          "type": "number"
        },
        "refinedTokens": {
          "type": "number"
        },
        "savedTokens": {
          "type": "number"
        },
        "reductionPercent": {
          "type": "string"
        },
        "fetchMs": {
          "type": "number"
        },
        "parseMs": {
          "type": "number"
        }
      },
      "required": [
        "hostname",
        "originalTokens",
        "refinedTokens",
        "savedTokens",
        "reductionPercent",
        "fetchMs",
        "parseMs"
      ],
      "additionalProperties": false
    }
  },
  "required": [
    "markdown",
    "stats"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢dompruner_analyze(url)

Returns a token-reduction analysis report for a URL. Shows render type (SSR/CSR/SSG), original vs refined token counts, reduction ratio, and top Semantic Anchors.

输入模式

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "URL to analyze."
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

输出模式

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string"
    },
    "renderType": {
      "type": "string",
      "description": "SSR, CSR, or SSG"
    },
    "originalTokens": {
      "type": "number"
    },
    "refinedTokens": {
      "type": "number"
    },
    "reductionPercent": {
      "type": "string"
    },
    "fetchMs": {
      "type": "number"
    },
    "parseMs": {
      "type": "number"
    },
    "topAnchors": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Top 5 semantic section headings."
    }
  },
  "required": [
    "url",
    "renderType",
    "originalTokens",
    "refinedTokens",
    "reductionPercent",
    "fetchMs",
    "parseMs",
    "topAnchors"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

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
已验证未记录版本2 个工具
已验证未记录版本2 个工具