search-mcp
Web search and clean-text page fetch for AI agents, with SSRF protection.
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
~229token 数(工具定义)
~1.0 KB典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.18%)
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": {
"search-mcp": {
"url": "https://search.ioconnex.dev/mcp"
}
}
}远程端点
https://search.ioconnex.dev/mcpstreamable-http它能做什么
工具清单
工具(2)
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢search_web(query, count)
Search the web and return titles, URLs, and snippets.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The search query."
},
"count": {
"default": 5,
"type": "integer",
"description": "Maximum results to return (1-10, default 5)."
}
},
"required": [
"query"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"result": {
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
}
},
"required": [
"result"
],
"x-fastmcp-wrap-result": true
}🟢fetch_url(url)
Fetch a public http(s) URL and return its main text content as plain text.
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The http(s) URL to fetch. Private/loopback hosts are rejected."
}
},
"required": [
"url"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"result": {
"type": "string"
}
},
"required": [
"result"
],
"x-fastmcp-wrap-result": true
}社区
证据
最近观测
已验证未记录版本2 个工具