Skip to main content
Glama
enesjakozh
marcopesani

serper-search-scrape-mcp-server

by marcopesani
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Serper 搜索和抓取 MCP 服务器

铁匠徽章

一个基于 TypeScript 的 MCP 服务器，使用 Serper API 提供网页搜索和网页抓取功能。该服务器与 Claude Desktop 集成，以实现强大的网页搜索和内容提取功能。

特征

工具

  • google_search - 通过 Serper API 执行网络搜索

    • 丰富的搜索结果，包括自然搜索结果、知识图谱、“人们还问”和相关搜索

    • 支持地区和语言定位

    • 位置、分页、时间过滤器和自动更正的可选参数

    • 支持高级搜索运算符：

      • site ：将结果限制在特定域

      • filetype ：限制为特定文件类型（例如“pdf”、“doc”）

      • inurl ：搜索 URL 中包含单词的页面

      • intitle ：搜索标题中包含单词的页面

      • related ：查找类似网站

      • cache ：查看特定 URL 的 Google 缓存版本

      • before ：之前的日期，格式为 YYYY-MM-DD

      • after ：之后的日期，格式为 YYYY-MM-DD

      • exact ：精确短语匹配

      • exclude ：从搜索结果中排除的术语

      • or ：替代术语（或运算符）

  • scrape从网页中提取内容

    • 获取纯文本和可选的 markdown 内容

    • 包括 JSON-LD 和头部元数据

    • 保留文档结构

Related MCP server: go_serper_mcp_server

要求

  • Node.js >= 18

  • Serper API 密钥（设置为SERPER_API_KEY环境变量）

发展

安装依赖项：

npm install

构建服务器：

npm run build

对于使用自动重建的开发：

npm run watch

运行测试：

npm test                  # Run all tests
npm run test:watch       # Run tests in watch mode
npm run test:coverage    # Run tests with coverage
npm run test:integration # Run integration tests

环境变量

在根目录中创建一个.env文件：

SERPER_API_KEY=your_api_key_here

调试

由于 MCP 服务器通过 stdio 进行通信，调试起来可能比较困难。我们推荐使用MCP Inspector ，它以包脚本的形式提供：

npm run inspector

检查器将提供一个 URL 来访问浏览器中的调试工具。

安装

通过 Smithery 安装

要通过Smithery自动安装 Serper Search and Scrape for Claude Desktop：

npx -y @smithery/cli install @marcopesani/mcp-server-serper --client claude

克劳德桌面

添加服务器配置：

  • MacOS： ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows： %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "serper-search": {
      "command": "npx",
      "args": ["-y", "serper-search-scrape-mcp-server"],
      "env": {
        "SERPER_API_KEY": "your_api_key_here"
      }
    }
  }
}

克莱恩

  1. 打开 Cline 扩展设置

  2. 打开“MCP 服务器”选项卡

  3. 点击“配置 MCP 服务器”

  4. 添加服务器配置：

{
  "mcpServers": {
    "github.com/marcopesani/mcp-server-serper": {
      "command": "npx",
      "args": ["-y", "serper-search-scrape-mcp-server"],
      "env": {
        "SERPER_API_KEY": "your_api_key_here"
      },
      "disabled": false,
      "autoApprove": ["google_search", "scrape"]
    }
  }
}

其他 Cline 配置选项：

  • disabled ：设置为false以启用服务器

  • autoApprove ：每次使用时不需要明确批准的工具列表

光标

  1. 打开光标设置

  2. 打开“功能”设置

  3. 在“MCP 服务器”部分，点击“添加新的 MCP 服务器”

  4. 选择一个名称，并选择“命令”作为“类型”

  5. 在“命令”字段中输入以下内容：

env SERPER_API_KEY=your_api_key_here npx -y serper-search-scrape-mcp-server

Docker

您也可以使用 Docker 运行服务器。首先，构建镜像：

docker build -t mcp-server-serper .

然后使用您的 Serper API 密钥运行容器：

docker run -e SERPER_API_KEY=your_api_key_here mcp-server-serper

或者，如果您的环境变量在.env文件中：

docker run --env-file .env mcp-server-serper

对于开发，您可能希望将源代码作为卷挂载：

docker run -v $(pwd):/app --env-file .env mcp-server-serper

注意：请确保将your_api_key_here替换为您的实际 Serper API 密钥。

Available Tools

2 tools
scrapeC

Tool to scrape a webpage and retrieve the text and, optionally, the markdown content. It will retrieve also the JSON-LD metadata and the head metadata.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesThe URL of the webpage to scrape.
includeMarkdownNoWhether to include markdown content.

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states what the tool retrieves (text, markdown, JSON-LD, head metadata) but lacks critical behavioral details such as rate limits, authentication needs, error handling, or whether it performs destructive actions (e.g., modifying data). For a web scraping tool with no annotation coverage, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded in a single sentence, efficiently stating the core functionality without unnecessary details. Every part earns its place, though it could be slightly more structured (e.g., separating outputs). It avoids redundancy and is appropriately sized for the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (web scraping with two parameters), no annotations, and no output schema, the description is partially complete. It covers what the tool retrieves but misses behavioral aspects like rate limits or error handling. Without an output schema, it should ideally describe return values more explicitly, but it does list the types of content retrieved, providing some context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, clearly documenting both parameters ('url' and 'includeMarkdown'). The description adds no additional meaning beyond the schema—it doesn't explain parameter interactions, constraints, or usage examples. With high schema coverage, the baseline score of 3 is appropriate as the schema handles the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'scrape a webpage and retrieve the text and, optionally, the markdown content. It will retrieve also the JSON-LD metadata and the head metadata.' This specifies the verb (scrape), resource (webpage), and outputs (text, markdown, JSON-LD, head metadata). However, it doesn't explicitly differentiate from the sibling tool 'google_search', which likely serves a different purpose (searching vs. scraping).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention the sibling tool 'google_search' or any other scraping-related tools, nor does it specify prerequisites, contexts, or exclusions for usage. This leaves the agent without clear direction on tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv1.0.0
    • First observedgoogle_search
    • First observedscrape
Deploy Server
Give agents eyes on the webHosted screenshot MCP. Send a URL, get a pixel-perfect image. $0.002 per grab. Works with Claude, Cursor, and Codex.grabbit.liveAd

TDQS

B3.3/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: google_search is for performing web searches and retrieving search results, while scrape is for extracting content from a specific webpage. There is no overlap in functionality, making it easy for an agent to choose the right tool for each task.

Naming Consistency5/5

Both tools follow a consistent naming pattern using snake_case with descriptive, action-oriented names (google_search and scrape). The naming is straightforward and predictable, with no deviations or mixed conventions.

Tool Count3/5

With only 2 tools, the server feels thin for a search-and-scrape domain, as it might lack additional utilities like batch processing, advanced filtering, or result summarization. However, the core functions are covered, making it borderline but functional.

Completeness4/5

The tools cover the essential workflows for search and scraping: performing searches and extracting webpage content. Minor gaps exist, such as no tool for managing search history or handling pagination, but agents can work around these with the provided tools.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • SerpApi MCP Server

    serpapi
    A
    license
    A
    quality
    A
    maintenance
    An MCP server that integrates with SerpApi to retrieve search results from multiple search engines including Google, Bing, Yahoo, and others, enabling fast access to both live and archived search data.
    3
    180
    MIT

  • go_serper_mcp_server

    hightemp
    A
    license
    Not graded
    quality
    D
    maintenance
    A Go-based MCP server that provides comprehensive access to the Serper Google Search API, including tools for images, news, maps, and scholar results. It also features a dedicated endpoint for scraping webpage content directly.
    8 npm
    MIT

  • mcp-searxng

    atomlong
    A
    license
    A
    quality
    D
    maintenance
    An MCP server that integrates the SearXNG API for web search and URL content extraction with advanced features like pagination, caching, and proxy support.
    4
    10,578 npm
    2
    MIT

Appeared in Searches