MCP 服务器

Nefesh — Real-Time Human State Awareness for AI

ai.nefesh/human-state
医疗健康 物联网与硬件 公开且可连接 MCP 2025-11-25

此 MCP 可以做什么

Processes biometric signals into a stress score for adapting AI interactions to a person's state.

check_api_key_status
Check a pending API key authorization using its request_id. Use request_id exactly as returned by request_api_key, never an email. Poll every 10 seconds. awaiting_user means the user must open the URL; pending means email verification is still required. ready returns the API key once only. Store it and include it in all subsequent HTTP calls. Stop on expired; ask the user before starting another authorization.
输入模式
{'type': 'object', 'title': 'CheckKeyStatusArguments', 'required': ['request_id'], 'properties': {'request_id': {'type': 'string', 'title': 'Request Id'}}, 'additionalProperties': False}
delete_subject
Permanently delete all sessions and trigger memory for a subject. Irreversible. Only call when the user explicitly requests this deletion.
可能执行破坏性操作 幂等
输入模式
{'type': 'object', 'title': 'delete_subjectArguments', 'required': ['subject_id'], 'properties': {'subject_id': {'type': 'string', 'title': 'Subject Id', 'maxLength': 256, 'minLength': 1}}}
get_human_state
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.
输入模式
{'type': 'object', 'title': 'get_human_stateArguments', 'required': ['session_id'], 'properties': {'session_id': {'type': 'string', 'title': 'Session Id'}}}
get_session_history
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.
输入模式
{'type': 'object', 'title': 'get_session_historyArguments', 'required': ['session_id'], 'properties': {'minutes': {'type': 'integer', 'title': 'Minutes', 'default': 5, 'maximum': 60, 'minimum': 1}, 'session_id': {'type': 'string', 'title': 'Session Id'}}}
get_trigger_memory
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.
输入模式
{'type': 'object', 'title': 'get_trigger_memoryArguments', 'required': ['subject_id'], 'properties': {'subject_id': {'type': 'string', 'title': 'Subject Id'}}}
ingest
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.
输入模式
{'type': 'object', 'title': 'ingestArguments', 'required': ['session_id', 'timestamp'], 'properties': {'eda': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Eda', 'default': None}, 'gaze': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Gaze', 'default': None}, 'sdnn': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Sdnn', 'default': None}, 'spo2': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Spo2', 'default': None}, 'tone': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Tone', 'default': None}, 'pnn50': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Pnn50', 'default': None}, 'rmssd': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Rmssd', 'default': None}, 'posture': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Posture', 'default': None}, 'urgency': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Urgency', 'default': None}, 'mean_ibi': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Mean Ibi', 'default': None}, 'ibi_count': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Ibi Count', 'default': None}, 'sentiment': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Sentiment', 'default': None}, 'timestamp': {'type': 'string', 'title': 'Timestamp'}, 'confidence': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Confidence', 'default': None}, 'engagement': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Engagement', 'default': None}, 'expression': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Expression', 'default': None}, 'heart_rate': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Heart Rate', 'default': None}, 'session_id': {'type': 'string', 'title': 'Session Id'}, 'subject_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Subject Id', 'default': None}, 'ai_response': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Ai Response', 'default': None}, 'sleep_stage': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Sleep Stage', 'default': None}, 'speech_rate': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Speech Rate', 'default': None}, 'stress_score': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Stress Score', 'default': None}, 'user_message': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'User Message', 'default': None}, 'glucose_mg_dl': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Glucose Mg Dl', 'default': None}, 'glucose_trend': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Glucose Trend', 'default': None}, 'source_device': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Source Device', 'default': None}, 'activity_level': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Activity Level', 'default': None}, 'cognitive_load': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Cognitive Load', 'default': None}, 'eeg_beta_power': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Eeg Beta Power', 'default': None}, 'glucose_mmol_l': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Glucose Mmol L', 'default': None}, 'eeg_alpha_power': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Eeg Alpha Power', 'default': None}, 'eeg_theta_power': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Eeg Theta Power', 'default': None}, 'respiratory_rate': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Respiratory Rate', 'default': None}, 'skin_temperature': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Skin Temperature', 'default': None}, 'pitch_variability': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'Pitch Variability', 'default': None}, 'steps_last_minute': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Steps Last Minute', 'default': None}}}
request_api_key
Start free API key authorization; no existing API key needed. Returns a verification_url. Ask the user to open that URL in their browser, enter their own email, then open the verification email and confirm access for their agent. This tool does not accept email addresses and does not send email. Do not choose, invent, or submit an email on the user's behalf. Poll check_api_key_status with the returned request_id at the supplied interval. Stop if the request expires. Never create new requests in a loop.
输入模式
{'type': 'object', 'title': 'RequestKeyArguments', 'properties': {}, 'additionalProperties': False}
已更改
check_api_key_status
2026年10月3日 02:59
已更改
request_api_key
2026年10月3日 02:59
已添加
delete_subject
2026年10月3日 02:59
已更改
get_session_history
2026年10月3日 02:59
已更改
ingest
2026年10月3日 02:59
已更改
get_human_state
2026年10月3日 02:59
已添加
check_api_key_status
2026年9月17日 07:57
已添加
request_api_key
2026年9月17日 07:57
已添加
get_session_history
2026年9月17日 07:57
已添加
get_trigger_memory
2026年9月17日 07:57
已添加
ingest
2026年9月17日 07:57
已添加
get_human_state
2026年9月17日 07:57