Nefesh — Real-Time Human State Awareness for AI
Fuses biometric signals into a stress score (0-100) for AI adaptation. MCP + A2A native.
我該用這個嗎
品質與安全性
發現項目（2）
- HIGHTool poisoning patterns detected
- LOWTool description contains role marker that could confuse chat models在 request_api_key 中
根據工具定義與協定合規性的自動化分析。
上下文成本
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": {
"human-state": {
"url": "https://mcp.nefesh.ai/mcp"
}
}
}遠端端點
https://mcp.nefesh.ai/mcpstreamable-http它能做什麼
工具清單
工具（6）
🟢get_human_state(session_id)
Get current unified human state for a session. Call this before generating important responses. Returns: - state: calm | relaxed | focused | stressed | acute_stress - stress_score: 0-100 (lower = calmer) - confidence: 0.0-1.0 (based on signal quality and device type) - suggested_action: maintain_engagement | simplify_and_focus | de-escalate_and_shorten | pause_and_ground - action_reason: human-readable explanation of why this action was suggested - adaptation_effectiveness (on 2nd+ call): shows whether your previous suggested_action actually reduced stress — contains previous_action, stress_delta, and effective boolean. Use this to self-improve. Use suggested_action to adapt your response: calm/relaxed = full complexity, focused = shorter and structured, stressed = max 2 sentences, acute_stress = one grounding sentence only. Requires a prior ingest call to have data. Not a medical device.
輸入結構描述
{
"type": "object",
"properties": {
"session_id": {
"title": "Session Id",
"type": "string"
}
},
"required": [
"session_id"
],
"title": "get_human_stateArguments"
}🟡ingest(session_id, timestamp, heart_rate, rmssd, sdnn, ...)
Send biometric signals from any sensor, get unified state back. Required: session_id + timestamp (ISO 8601) + at least one signal. Send whatever you have — the API fuses all signals into one state. Common signals (highest impact): - heart_rate (bpm, 30-220) + rmssd (ms) — cardiovascular - tone: calm | tense | anxious | hostile — vocal - sentiment: -1.0 to 1.0 — textual - expression: relaxed | neutral | tense — visual For trigger memory (cross-session psychological tracking): - Include subject_id (consistent per user, hashed) Returns same fields as get_human_state plus signals_received list and topics_detected (if conversation text was included). source_device is optional but improves confidence scoring. Not a medical device.
輸入結構描述
{
"type": "object",
"properties": {
"session_id": {
"title": "Session Id",
"type": "string"
},
"timestamp": {
"title": "Timestamp",
"type": "string"
},
"heart_rate": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Heart Rate"
},
"rmssd": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Rmssd"
},
"sdnn": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Sdnn"
},
"spo2": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Spo2"
},
"pnn50": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Pnn50"
},
"mean_ibi": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Mean Ibi"
},
"ibi_count": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Ibi Count"
},
"tone": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Tone"
},
"speech_rate": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Speech Rate"
},
"pitch_variability": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Pitch Variability"
},
"expression": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Expression"
},
"gaze": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Gaze"
},
"posture": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Posture"
},
"engagement": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Engagement"
},
"sentiment": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Sentiment"
},
"urgency": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Urgency"
},
"glucose_mg_dl": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Glucose Mg Dl"
},
"glucose_mmol_l": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Glucose Mmol L"
},
"glucose_trend": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Glucose Trend"
},
"eeg_alpha_power": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Eeg Alpha Power"
},
"eeg_beta_power": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Eeg Beta Power"
},
"eeg_theta_power": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Eeg Theta Power"
},
"cognitive_load": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Cognitive Load"
},
"eda": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Eda"
},
"skin_temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Skin Temperature"
},
"respiratory_rate": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Respiratory Rate"
},
"steps_last_minute": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Steps Last Minute"
},
"activity_level": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Activity Level"
},
"sleep_stage": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Sleep Stage"
},
"stress_score": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Stress Score"
},
"source_device": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Source Device"
},
"confidence": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Confidence"
},
"subject_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Subject Id"
}
},
"required": [
"session_id",
"timestamp"
],
"title": "ingestArguments"
}🟢get_trigger_memory(subject_id)
Retrieve psychological trigger profile for a subject. Returns which conversation topics consistently cause stress (active triggers) and which have been resolved over time. - active triggers: topics where stress was elevated across multiple sessions. Tread carefully. - resolved triggers: topics where stress has decreased. Safe to explore deeper. Each trigger includes observation_count, avg_score, peak_score, and last_seen. Requires prior ingest calls with the same subject_id. Not a medical device.
輸入結構描述
{
"type": "object",
"properties": {
"subject_id": {
"title": "Subject Id",
"type": "string"
}
},
"required": [
"subject_id"
],
"title": "get_trigger_memoryArguments"
}🟢get_session_history(session_id, minutes)
Get state history for a session over time. Returns timestamped datapoints with stress_score, state, and heart_rate for each observation. Includes an overall trend: rising | falling | stable. Use minutes parameter to control the lookback window (default: 5, max: 60). Useful for detecting stress patterns during a conversation. Not a medical device.
輸入結構描述
{
"type": "object",
"properties": {
"session_id": {
"title": "Session Id",
"type": "string"
},
"minutes": {
"default": 5,
"title": "Minutes",
"type": "integer"
}
},
"required": [
"session_id"
],
"title": "get_session_historyArguments"
}🟢request_api_key(email)
Request a free Nefesh API key. No existing API key needed for this call. IMPORTANT: You MUST ask the user for their real email address before calling this tool. Do NOT invent, guess, or generate an email address. The user will receive a verification link they must click to activate the key. Without clicking that link, no API key will be issued. Disposable or temporary email services are blocked. Example prompt to the user: "What is your email address? You will receive a verification link to activate your free API key." Flow: call this with the user's real email, then poll check_api_key_status every 10 seconds until status is 'ready'. Free tier: 1,000 calls/month, all signal types, 10 req/min. No credit card.
輸入結構描述
{
"type": "object",
"properties": {
"email": {
"title": "Email",
"type": "string"
}
},
"required": [
"email"
],
"title": "request_api_keyArguments"
}🟢check_api_key_status(request_id)
Check the status of a pending API key request. Use the exact same email the user provided to request_api_key. Poll this every 10 seconds. Once the user clicks the verification link in their inbox, status changes from 'pending' to 'ready' and the response includes the API key. Store it immediately — returned once only. Expires after 15 minutes.
輸入結構描述
{
"type": "object",
"properties": {
"request_id": {
"title": "Request Id",
"type": "string"
}
},
"required": [
"request_id"
],
"title": "check_api_key_statusArguments"
}建議的提示詞
get_human_stateget_human_state社群
證據