llms-txt-validator
Validate a site's llms.txt against the spec: fetches every linked URL, scores it 0-100.
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
~247token 数（工具定义）
~498 B典型响应大小
对注意力的影响极小（占 128k 上下文窗口的 0.19%）
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": {
"llms-txt-validator": {
"url": "https://llms-txt-validator.dev/mcp"
}
}
}远程端点
https://llms-txt-validator.dev/mcpstreamable-http它能做什么
工具清单
工具（3）
🟢 只读🟡 写入🔴 删除⚪ 未知
⚪validate_llms_txt(url)
Validate a website's llms.txt: returns a 0-100 quality score, findings, and AI-discoverability signals. Pass a domain or URL.
输入模式
{
"type": "object",
"properties": {
"url": {
"description": "Domain or URL to check, e.g. \"example.com\". A path checks that path's llms.txt (spec v2), e.g. \"example.com/docs\".",
"type": "string"
}
},
"required": [
"url"
]
}⚪validate_llms_txt_content(content)
Validate raw llms.txt text you already hold, without fetching it. Returns the same score and findings.
输入模式
{
"type": "object",
"properties": {
"content": {
"description": "The full llms.txt file contents (Markdown) to validate.",
"type": "string"
}
},
"required": [
"content"
]
}⚪generate_llms_txt(url)
Scaffold a starter llms.txt for a domain from its homepage and sitemap.
输入模式
{
"type": "object",
"properties": {
"url": {
"description": "Domain to scaffold, e.g. \"example.com\".",
"type": "string"
}
},
"required": [
"url"
]
}社区
证据
最近观测
已验证未记录版本3 个工具