AfterImage
Shared copies of public web pages for AI agents. Search stored pages or fetch a URL.
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
~251token 数（工具定义）
~888 B典型响应大小
对注意力的影响极小（占 128k 上下文窗口的 0.20%）
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": {
"afterimage": {
"url": "https://afterimage.page/mcp"
}
}
}远程端点
https://afterimage.page/mcpstreamable-http它能做什么
工具清单
工具（2）
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢get_page(url, max_age_s)
Return readable text for a public http(s) URL. Reuses a stored copy if it is newer than max_age_s. Includes sha256 hash and fetched_at. Needs a funded API key on this HTTP request.
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Absolute http(s) URL to snapshot."
},
"max_age_s": {
"type": "integer",
"minimum": 0,
"default": 900,
"description": "Reuse a cached snapshot if it is no older than this many seconds."
}
},
"required": [
"url"
]
}🟢search_pages(q, limit, max_age_s)
Search pages already stored in AfterImage. Does not visit the live web. Then call get_page for the full text of a hit. Needs a funded API key.
输入模式
{
"type": "object",
"properties": {
"q": {
"type": "string",
"description": "Search the already-fetched corpus. Does not hit the live web."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 10
},
"max_age_s": {
"type": "integer",
"minimum": 0,
"description": "Only return snapshots no older than this many seconds."
}
},
"required": [
"q"
]
}社区
证据
最近观测
已验证未记录版本2 个工具
已验证未记录版本2 个工具
已验证未记录版本2 个工具