Web Content Extract Mcp
Web Content Extract Mcp connects AI agents to real public APIs via MCP. Tools include
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
~363token 数（工具定义）
~426 B典型响应大小
对注意力的影响极小（占 128k 上下文窗口的 0.28%）
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": {
"web_content_extract_mcp": {
"url": "https://web-content-extract-mcp.mcpize.run/mcp"
}
}
}远程端点
https://web-content-extract-mcp.mcpize.run/mcpstreamable-http它能做什么
工具清单
工具（5）
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢fetch_url_content(url, max_chars)
Fetch and extract clean text content from a public URL. Returns: {title, text, url, word_count}
输入模式
{
"type": "object",
"properties": {
"url": {
"title": "Url",
"type": "string"
},
"max_chars": {
"default": 5000,
"title": "Max Chars",
"type": "integer"
}
},
"required": [
"url"
],
"title": "fetch_url_contentArguments"
}🟢extract_article(url)
Extract main article content from a news/blog URL. Returns: {title, description, body, author, date}
输入模式
{
"type": "object",
"properties": {
"url": {
"title": "Url",
"type": "string"
}
},
"required": [
"url"
],
"title": "extract_articleArguments"
}🟢get_page_links(url, same_domain_only)
Extract all links from a page. Returns: {links: [href], internal_count, external_count}
输入模式
{
"type": "object",
"properties": {
"url": {
"title": "Url",
"type": "string"
},
"same_domain_only": {
"default": true,
"title": "Same Domain Only",
"type": "boolean"
}
},
"required": [
"url"
],
"title": "get_page_linksArguments"
}🟢get_page_metadata(url)
Get metadata from a page: title, description, og tags, keywords. Returns: {title, description, keywords, og_title, og_image, og_type}
输入模式
{
"type": "object",
"properties": {
"url": {
"title": "Url",
"type": "string"
}
},
"required": [
"url"
],
"title": "get_page_metadataArguments"
}🟢health_check
Server health check.
输入模式
{
"type": "object",
"properties": {},
"title": "health_checkArguments"
}社区
证据
最近观测
已验证未记录版本5 个工具
已验证未记录版本5 个工具
已验证未记录版本5 个工具