UsageMax public observability
Read-only MCP for AI usage profiles, leaderboards, stats, and docs; no writes or private data.
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
~410token 数（工具定义）
~695 B典型响应大小
对注意力的影响极小（占 128k 上下文窗口的 0.32%）
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": {
"usagemax": {
"url": "https://usagemax.com/mcp"
}
}
}远程端点
https://usagemax.com/mcpstreamable-http它能做什么
工具清单
工具（4）
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢public_profile(handle)
Read one opt-in public UsageMax profile and aggregate statistics.
输入模式
{
"type": "object",
"properties": {
"handle": {
"type": "string",
"minLength": 1,
"maxLength": 80,
"description": "The public profile handle, without the @ prefix."
}
},
"required": [
"handle"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"additionalProperties": true
}🟢leaderboard(metric, period)
Read the public UsageMax leaderboard (maximum 100 rows).
输入模式
{
"type": "object",
"properties": {
"metric": {
"type": "string",
"enum": [
"tokens",
"spend"
],
"default": "tokens",
"description": "Rank by aggregate tokens or tracked spend."
},
"period": {
"type": "string",
"enum": [
"7d",
"30d",
"all"
],
"default": "all",
"description": "Choose the bounded reporting window."
}
},
"required": [],
"additionalProperties": false
}输出模式
{
"type": "object",
"additionalProperties": true
}🟢network_stats
Read aggregate public UsageMax network statistics and render the optional inline observability view.
输入模式
{
"type": "object",
"properties": {},
"required": [],
"additionalProperties": false
}输出模式
{
"type": "object",
"additionalProperties": true
}🟢ask_site(query)
Ask a bounded natural-language question about UsageMax and receive cited public resources.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 500
}
},
"required": [
"query"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"additionalProperties": true
}社区
证据
最近观测
已验证未记录版本4 个工具
已验证未记录版本4 个工具
已验证未记录版本4 个工具