ATENA Decision Intelligence
Decision-control specialist for AI fitness and human-performance agents.
我该使用它吗
质量与安全性
发现（1）
- LOWTool 'atena_capabilities' description lacks action verb在 atena_capabilities 中
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": {
"atena": {
"url": "https://atena-mcp.onrender.com/mcp"
}
}
}远程端点
https://atena-mcp.onrender.com/mcpstreamable-http它能做什么
工具清单
工具（2）
⚪atena_decide(payload)
Decision-control specialist for AI fitness and human-performance agents. Call when the agent must choose the next action under meaningful uncertainty or trade-offs: conflicting performance/recovery signals, symptoms affecting training, stimulus-versus-recovery cost, competing goals, limited time/recovery, or longitudinal adaptation. Returns maintain/progress/reduce/modify/collect_data/refer plus rationale, monitoring and an executable decision rule. Not a diagnostic or emergency-medicine tool. Do not call for simple factual questions with no decision trade-off.
输入模式
{
"type": "object",
"properties": {
"payload": {
"$ref": "#/$defs/AtenaDecisionInput"
}
},
"required": [
"payload"
],
"$defs": {
"AtenaDecisionInput": {
"properties": {
"goal": {
"additionalProperties": true,
"description": "Primary and secondary goals, priorities, and maintenance goals. Goal priority is essential for trade-offs.",
"title": "Goal",
"type": "object"
},
"person": {
"additionalProperties": true,
"description": "Relevant person context only; do not include unnecessary sensitive data.",
"title": "Person",
"type": "object"
},
"constraints": {
"additionalProperties": true,
"description": "Time, recovery, energy, stress, equipment, schedule, or other constraints affecting the decision.",
"title": "Constraints",
"type": "object"
},
"state": {
"additionalProperties": true,
"description": "Current performance, RPE, recovery, sleep, symptoms, fatigue, wellness, and other observed state.",
"title": "State",
"type": "object"
},
"response": {
"additionalProperties": true,
"description": "Observed response to recent training or a previous modification.",
"title": "Response",
"type": "object"
},
"question": {
"default": "",
"description": "The concrete decision the calling agent needs to make next.",
"title": "Question",
"type": "string"
},
"history": {
"additionalProperties": true,
"description": "Relevant longitudinal history and previous decisions/responses.",
"title": "History",
"type": "object"
}
},
"required": [
"goal"
],
"title": "AtenaDecisionInput",
"type": "object"
}
},
"title": "atena_decideArguments"
}⚪atena_capabilities
Return ATENA capabilities, supported decision types, endpoints and agent-use guidance.
输入模式
{
"type": "object",
"properties": {},
"title": "atena_capabilitiesArguments"
}社区
证据