ai-rate-limit-tracker
Cloudflare Workers MCP server: ai-rate-limit-tracker
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
~317token 数（工具定义）
~580 B典型响应大小
对注意力的影响极小（占 128k 上下文窗口的 0.25%）
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": {
"ai-rate-limit-tracker": {
"url": "https://api.lazy-mac.com/ai-rate-limit-tracker/mcp"
}
}
}远程端点
https://api.lazy-mac.com/ai-rate-limit-tracker/mcpstreamable-http它能做什么
工具清单
工具（4）
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢get_provider_limits(provider, model)
Get published rate limit specs (RPM, TPM, RPD, context window) for an AI provider and optional model.
输入模式
{
"type": "object",
"properties": {
"provider": {
"type": "string",
"description": "openai | anthropic | gemini | groq | cohere | mistral | together | deepseek"
},
"model": {
"type": "string",
"description": "Model name (optional)"
}
},
"required": [
"provider"
]
}🟢list_providers
List all AI providers supported by the tracker with their models and default limits.
输入模式
{
"type": "object",
"properties": {},
"required": []
}🟢track_usage(api_key, provider, model, tokens_used, latency_ms)
Record an AI API call and get real-time usage counters plus warnings if approaching limits.
输入模式
{
"type": "object",
"properties": {
"api_key": {
"type": "string",
"description": "Your tracker API key"
},
"provider": {
"type": "string"
},
"model": {
"type": "string"
},
"tokens_used": {
"type": "integer"
},
"latency_ms": {
"type": "integer"
}
},
"required": [
"api_key",
"provider"
]
}🟢get_forecast(api_key, provider, model, rate_rpm)
Forecast when rate limits will be exhausted and get scheduling recommendations.
输入模式
{
"type": "object",
"properties": {
"api_key": {
"type": "string"
},
"provider": {
"type": "string"
},
"model": {
"type": "string"
},
"rate_rpm": {
"type": "number",
"description": "Your actual request rate (requests/min)"
}
},
"required": [
"api_key",
"provider"
]
}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