SmartFetch
Paid fallback for public webpages: clean text, Markdown, links, metadata, and JavaScript rendering.
我该使用它吗
质量与安全性
A
基于对工具定义和协议合规性的自动分析。
上下文开销
~443token 数（工具定义）
~839 B典型响应大小
对注意力的影响极小（占 128k 上下文窗口的 0.35%）
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": {
"smartfetch": {
"url": "https://smartfetch-production-ea53.up.railway.app/mcp"
}
}
}远程端点
https://smartfetch-production-ea53.up.railway.app/mcpstreamable-http它能做什么
工具清单
工具（4）
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢fetch_webpage(url, max_chars, force_browser)
Read, fetch, scrape, or extract any public webpage or URL for AI agents. Returns clean text, Markdown, links, and metadata, with automatic browser rendering for JavaScript-heavy pages.
输入模式
{
"type": "object",
"properties": {
"url": {
"title": "Url",
"type": "string"
},
"max_chars": {
"default": 20000,
"maximum": 50000,
"minimum": 1000,
"title": "Max Chars",
"type": "integer"
},
"force_browser": {
"default": false,
"title": "Force Browser",
"type": "boolean"
}
},
"required": [
"url"
],
"title": "fetch_webpageArguments"
}⚪webpage_to_markdown(url, max_chars, force_browser)
Convert a public webpage or URL into clean Markdown for AI agents, with core retrieval metadata.
输入模式
{
"type": "object",
"properties": {
"url": {
"title": "Url",
"type": "string"
},
"max_chars": {
"default": 20000,
"maximum": 50000,
"minimum": 1000,
"title": "Max Chars",
"type": "integer"
},
"force_browser": {
"default": false,
"title": "Force Browser",
"type": "boolean"
}
},
"required": [
"url"
],
"title": "webpage_to_markdownArguments"
}🟢extract_webpage_text(url, max_chars, force_browser)
Extract clean readable text from a public webpage or URL for AI agents, with core retrieval metadata.
输入模式
{
"type": "object",
"properties": {
"url": {
"title": "Url",
"type": "string"
},
"max_chars": {
"default": 20000,
"maximum": 50000,
"minimum": 1000,
"title": "Max Chars",
"type": "integer"
},
"force_browser": {
"default": false,
"title": "Force Browser",
"type": "boolean"
}
},
"required": [
"url"
],
"title": "extract_webpage_textArguments"
}⚪render_webpage(url, max_chars)
Browser-render a public JavaScript-heavy webpage or URL, then return clean text, Markdown, links, and metadata.
输入模式
{
"type": "object",
"properties": {
"url": {
"title": "Url",
"type": "string"
},
"max_chars": {
"default": 20000,
"maximum": 50000,
"minimum": 1000,
"title": "Max Chars",
"type": "integer"
}
},
"required": [
"url"
],
"title": "render_webpageArguments"
}社区
证据
最近观测
已验证未记录版本4 个工具
已验证未记录版本4 个工具
已验证未记录版本4 个工具