Fetch MCP Server
获取 MCP 服务器

该 MCP 服务器提供获取各种格式的 Web 内容的功能,包括 HTML、JSON、纯文本和 Markdown。
成分
工具
fetch_html
获取网站并以 HTML 格式返回内容
输入:
url(字符串,必需):要获取的网站的 URLheaders(对象,可选):包含在请求中的自定义标头
返回网页的原始 HTML 内容
fetch_json
从 URL 获取 JSON 文件
输入:
url(字符串,必需):要获取的 JSON 的 URLheaders(对象,可选):包含在请求中的自定义标头
返回解析后的 JSON 内容
获取文本
获取网站并以纯文本形式返回内容(无 HTML)
输入:
url(字符串,必需):要获取的网站的 URLheaders(对象,可选):包含在请求中的自定义标头
返回删除了 HTML 标签、脚本和样式的网页文本内容
fetch_markdown
获取网站并以 Markdown 格式返回内容
输入:
url(字符串,必需):要获取的网站的 URLheaders(对象,可选):包含在请求中的自定义标头
返回转换为Markdown格式的网页内容
资源
此服务器不提供任何持久性资源。其设计旨在按需获取和转换 Web 内容。
Related MCP server: Fetch MCP Server
入门
克隆存储库
安装依赖项:
npm install构建服务器:
npm run build
用法
要使用服务器,您可以直接运行它:
npm start这将启动在 stdio 上运行的 Fetch MCP 服务器。
与桌面应用程序一起使用
要将此服务器与桌面应用程序集成,请将以下内容添加到应用程序的服务器配置中:
{
"mcpServers": {
"fetch": {
"command": "node",
"args": [
"{ABSOLUTE PATH TO FILE HERE}/dist/index.js"
]
}
}
}特征
使用现代 fetch API 获取网页内容
支持自定义请求头
提供多种格式的内容:HTML、JSON、纯文本和Markdown
使用 JSDOM 进行 HTML 解析和文本提取
使用 TurndownService 将 HTML 转换为 Markdown
发展
运行
npm run dev以监视模式启动 TypeScript 编译器使用
npm test运行测试套件
执照
该项目已获得 MIT 许可。
Available Tools
4 toolsfetch_htmlC
Fetch a website and return its unmodified contents as HTML
Inputs: url (required), headers, max_length, start_index.
fetch_jsonC
Fetch a JSON file from a URL
Inputs: url (required), headers, max_length, start_index.
fetch_markdownC
Fetch a website and return its contents converted content to Markdown
Inputs: url (required), headers, max_length, start_index.
fetch_txtA
Fetch a website, convert the content to plain text (no HTML)
Inputs: url (required), headers, max_length, start_index.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: fetch_html returns raw HTML, fetch_json retrieves JSON files, fetch_markdown converts to Markdown, and fetch_txt extracts plain text. There is no ambiguity or overlap in functionality, making it easy for an agent to select the correct tool based on the desired output format.
All tool names follow a consistent verb_noun pattern with 'fetch_' prefix and descriptive suffixes (html, json, markdown, txt). This predictable naming scheme enhances readability and usability, allowing agents to intuitively understand each tool's function without confusion.
With 4 tools, the server is well-scoped for its purpose of fetching and converting web content. Each tool earns its place by covering distinct output formats (HTML, JSON, Markdown, plain text), avoiding bloat while providing comprehensive coverage for common web data retrieval needs.
The tool set provides complete coverage for the domain of fetching web content in various formats. It includes raw HTML, structured JSON, and converted formats (Markdown and plain text), leaving no obvious gaps. Agents can handle a wide range of web data retrieval scenarios without dead ends.
Maintenance
Related MCP Connectors
Fetch any URL as clean markdown, HTML, or a screenshot for AI agents.
Fetch public web pages live and get clean Markdown, text or HTML.
Fetch public web pages live and get clean Markdown, text or HTML.
Fetch public web pages live and get clean Markdown, text or HTML.
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides functionality to fetch web content in various formats, including HTML, JSON, plain text, and Markdown.4117,041 npm2MIT
- AlicenseBqualityDmaintenanceProvides functionality to fetch web content in various formats, including HTML, JSON, plain text, and Markdown with support for custom headers.43MIT
- AlicenseNot gradedqualityCmaintenanceProvides functionality to fetch and transform web content in various formats (HTML, JSON, plain text, and Markdown) through simple API calls.117,041 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables fetching and converting web content into various formats including HTML, JSON, plain text, and Markdown. It supports custom request headers and provides specialized tools for on-demand web data retrieval and transformation.MIT