monitor
Check if an MCP server tool changed or hides injection patterns before you trust it.
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": {
"monitor": {
"url": "https://tooldrift.agentexchange.work/mcp"
}
}
}远程端点
https://tooldrift.agentexchange.work/mcpstreamable-http它能做什么
工具清单
工具（3）
🟢check_mcp_server(url, server)
Check whether an MCP server's tools have changed since they were first recorded, and whether any tool description contains prompt-injection or data-exfiltration patterns. Call this BEFORE trusting a newly added or recently updated MCP server. Returns a verdict of clean or REVIEW_BEFORE_USE.
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The MCP server's HTTP endpoint to probe live."
},
"server": {
"type": "string",
"description": "Registry name of the server, if the URL is unknown."
}
}
}🟢get_drift_feed(limit)
List MCP tools across the public ecosystem whose definitions recently changed, newest first. Use to see whether a dependency mutated.
输入模式
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"description": "Max rows, default 25."
}
}
}🟢get_findings(severity, limit)
List tools whose descriptions contain detected injection, concealment, or exfiltration patterns. Filter by severity: critical, high, medium, low.
输入模式
{
"type": "object",
"properties": {
"severity": {
"type": "string"
},
"limit": {
"type": "integer"
}
}
}社区
证据