agentsearch-mcp
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
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": {
"agentsearch-mcp": {
"url": "https://agentsearch-mcp.vercel.app/mcp"
}
}
}远程端点
https://agentsearch-mcp.vercel.app/mcpstreamable-http它能做什么
工具清单
工具（3）
🟢web_search(q, provider, limit, country)
Search the web via a provider-abstracted backend (Brave or Serper, configured operator-side). Returns normalized results, each with position, title, url, snippet, source, and domain, plus a meta envelope (cache state, provider, took_ms). Returns a provider_required error if no search provider key is configured upstream. Use this for a full web SERP; use instant_answer for quick facts/definitions.
输入模式
{
"type": "object",
"properties": {
"q": {
"type": "string",
"description": "Search query."
},
"provider": {
"description": "Force a specific provider. Omit to use whichever is configured operator-side.",
"type": "string",
"enum": [
"brave",
"serper"
]
},
"limit": {
"description": "Max results, clamped to 1-20. Default 10.",
"type": "integer",
"minimum": 1,
"maximum": 20
},
"country": {
"description": "ISO-3166 alpha-2 region, lowercase. Default us.",
"type": "string"
}
},
"required": [
"q"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢instant_answer(q)
DuckDuckGo Instant Answer API — definitions, entities, and quick facts. Returns a normalized answer with heading, type (abstract/answer/disambiguation), source, sourceUrl, optional image/definition, and relatedTopics, plus a meta envelope. Not a full web SERP; use web_search for that. Works with no API key.
输入模式
{
"type": "object",
"properties": {
"q": {
"type": "string",
"description": "Query."
}
},
"required": [
"q"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢fetch_url(url, format, maxChars, links)
Fetches any public http(s) URL, strips boilerplate (scripts, nav, footer, ads), and returns clean text or markdown ready for an LLM context window. SSRF-guarded — refuses private/loopback/internal hosts. Returns url, title, format, length, content (and finalUrl when redirected, plus up to 50 extracted links when links=true), with a meta envelope. Works with no API key.
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The URL to fetch (public http/https only)."
},
"format": {
"description": "Output format. Default text.",
"type": "string",
"enum": [
"text",
"markdown"
]
},
"maxChars": {
"description": "Max characters of content returned, clamped 500-500000. Default 100000.",
"type": "integer",
"minimum": 500,
"maximum": 500000
},
"links": {
"description": "Also return up to 50 extracted links. Default false.",
"type": "boolean"
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}社区
证据