UsageMax public observability
Read-only MCP for AI usage profiles, leaderboards, stats, and docs; no writes or private data.
我該用這個嗎
品質與安全性
A
根據工具定義與協定合規性的自動化分析。
上下文成本
~410Token（工具定義）
~695 B典型回應大小
極小的注意力影響（128k 上下文的 0.32%）
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"usagemax": {
"url": "https://usagemax.com/mcp"
}
}
}遠端端點
https://usagemax.com/mcpstreamable-http它能做什麼
工具清單
工具（4）
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢public_profile(handle)
Read one opt-in public UsageMax profile and aggregate statistics.
輸入結構描述
{
"type": "object",
"properties": {
"handle": {
"type": "string",
"minLength": 1,
"maxLength": 80,
"description": "The public profile handle, without the @ prefix."
}
},
"required": [
"handle"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"additionalProperties": true
}🟢leaderboard(metric, period)
Read the public UsageMax leaderboard (maximum 100 rows).
輸入結構描述
{
"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
}輸出結構描述
{
"type": "object",
"additionalProperties": true
}🟢network_stats
Read aggregate public UsageMax network statistics and render the optional inline observability view.
輸入結構描述
{
"type": "object",
"properties": {},
"required": [],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"additionalProperties": true
}🟢ask_site(query)
Ask a bounded natural-language question about UsageMax and receive cited public resources.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 500
}
},
"required": [
"query"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"additionalProperties": true
}社群
證據
近期觀測
已驗證未記錄版本4 個工具
已驗證未記錄版本4 個工具
已驗證未記錄版本4 個工具