{"name":"ai.nefesh/human-state","title":"Nefesh — Real-Time Human State Awareness for AI","url":"https://mcp.nefesh.ai/mcp","host":"mcp.nefesh.ai","read_at":"2026-11-10T15:26:19.326217+00:00","grade":"A","score":100,"capped":null,"graded":true,"pending_second_read":[],"counts":{"error":0,"warning":0,"info":1},"findings":[{"rule":"mcp-version-differs","severity":"info","message":"The version it reports differs from its newest registry entry. It reports 1.26.0; the registry lists 4.0.0.","fix":"","where":[],"count":0}],"handshake":{"answered":true,"mcp":true,"era":"handshake","protocol_version":"2025-11-25","server_info":{"name":"nefesh","version":"1.26.0","title":null},"capabilities":["experimental","prompts","resources","tools"]},"sign_in":null,"tools":[{"name":"get_human_state","title":null,"description":"Get current unified human state for a session. Call this before generating important responses.\n\n    Returns:\n    - state: calm | relaxed | focused | stressed | acute_stress\n    - stress_score: 0-100 (lower = calmer)\n    - confidence: 0.0-1.0 (based on signal quality and device type)\n    - suggested_action: maintain_engagement | simplify_and_focus | de-escalate_and_shorten | pause_and_ground\n    - action_reason: human-readable explanation of why this action was suggested\n    - 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.\n\n    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.\n\n    Requires a prior ingest call to have data. Not a medical device.\n    ","read_only":null,"destructive":null,"inputs":["session_id"],"required":["session_id"],"price_stated_usd":null},{"name":"ingest","title":null,"description":"Send biometric signals from any sensor, get unified state back.\n\n    Required: session_id + timestamp (ISO 8601) + at least one signal.\n    Send whatever you have — the API fuses all signals into one state.\n\n    Common signals (highest impact):\n    - heart_rate (bpm, 30-220) + rmssd (ms) — cardiovascular\n    - tone: calm | tense | anxious | hostile — vocal\n    - sentiment: -1.0 to 1.0 — textual\n    - expression: relaxed | neutral | tense — visual\n\n    For trigger memory (cross-session psychological tracking):\n    - Include subject_id (consistent per user, hashed)\n\n    Returns same fields as get_human_state plus signals_received list and topics_detected (if conversation text was included).\n\n    source_device is optional but improves confidence scoring. Not a medical device.\n    ","read_only":null,"destructive":null,"inputs":["session_id","timestamp","heart_rate","rmssd","sdnn","spo2","pnn50","mean_ibi","ibi_count","tone","speech_rate","pitch_variability","expression","gaze","posture","engagement","sentiment","urgency","glucose_mg_dl","glucose_mmol_l","glucose_trend","eeg_alpha_power","eeg_beta_power","eeg_theta_power","cognitive_load","eda","skin_temperature","respiratory_rate","steps_last_minute","activity_level","sleep_stage","stress_score","source_device","confidence","subject_id","user_message","ai_response"],"required":["session_id","timestamp"],"price_stated_usd":null},{"name":"get_trigger_memory","title":null,"description":"Retrieve psychological trigger profile for a subject.\n\n    Returns which conversation topics consistently cause stress (active triggers) and which have been resolved over time.\n\n    - active triggers: topics where stress was elevated across multiple sessions. Tread carefully.\n    - resolved triggers: topics where stress has decreased. Safe to explore deeper.\n\n    Each trigger includes observation_count, avg_score, peak_score, and last_seen.\n\n    Requires prior ingest calls with the same subject_id. Not a medical device.\n    ","read_only":null,"destructive":null,"inputs":["subject_id"],"required":["subject_id"],"price_stated_usd":null},{"name":"get_session_history","title":null,"description":"Get state history for a session over time.\n\n    Returns timestamped datapoints with stress_score, state, and heart_rate for each observation.\n    Includes an overall trend: rising | falling | stable.\n\n    Use minutes parameter to control the lookback window (default: 5, max: 60).\n    Useful for detecting stress patterns during a conversation. Not a medical device.\n    ","read_only":null,"destructive":null,"inputs":["session_id","minutes"],"required":["session_id"],"price_stated_usd":null},{"name":"delete_subject","title":null,"description":"Permanently delete all sessions and trigger memory for a subject.\n\n    Irreversible. Only call when the user explicitly requests this deletion.\n    ","read_only":null,"destructive":true,"inputs":["subject_id"],"required":["subject_id"],"price_stated_usd":null},{"name":"request_api_key","title":null,"description":"Start free API key authorization; no existing API key needed.\n\n    Returns a verification_url. Ask the user to open that URL in their\n    browser, enter their own email, then open the verification email and\n    confirm access for their agent. This tool\n    does not accept email addresses and does not send email.\n    Do not choose, invent, or submit an email on the user's behalf.\n    Poll check_api_key_status with the returned request_id at the supplied\n    interval. Stop if the request expires. Never create new requests in a loop.\n    ","read_only":null,"destructive":null,"inputs":[],"required":[],"price_stated_usd":null},{"name":"check_api_key_status","title":null,"description":"Check a pending API key authorization using its request_id.\n\n    Use request_id exactly as returned by request_api_key, never an email.\n    Poll every 10 seconds. awaiting_user means the user must open the URL;\n    pending means email verification is still required. ready returns the\n    API key once only. Store it and include it in all subsequent HTTP calls.\n    Stop on expired; ask the user before starting another authorization.\n    ","read_only":null,"destructive":null,"inputs":["request_id"],"required":["request_id"],"price_stated_usd":null}],"tools_listed":7,"samples":[],"price_honesty":"nothing to check","tls":{"valid":true,"expires_on":"2026-12-23","days_after_check":43,"issuer":"Let's Encrypt"},"registry":{"version":"4.0.0","status":200,"published_at":"2026-04-03T19:42:18.337564Z","website_url":null,"repository":"https://github.com/nefesh-ai/nefesh-mcp-server"},"robots":null,"reads":1,"card_url":"https://agoranome.com/mcp-servers/ai.nefesh/human-state","badge":{"url":"https://agoranome.com/mcp-servers/ai.nefesh/human-state/badge.svg","markdown":"[![Agoranome MCP report card](https://agoranome.com/mcp-servers/ai.nefesh/human-state/badge.svg)](https://agoranome.com/mcp-servers/ai.nefesh/human-state)"},"method":"Read the way an MCP client reads a server before an agent uses it: the handshake, every page of the tool list, the prompts and resources, the sign-in challenge, the server card and the TLS certificate, once a week, with no payment and nothing that writes. Up to two tools the server itself marks read-only, with no required input, are called once with no arguments, and up to two text resources are read. Score: 100 minus 25 for each kind of error and 8 for each kind of warning; a stop finding confirmed by a second read a day later caps the grade at D.","method_url":"https://agoranome.com/mcp-servers/method","method_version":1,"paid_next":{"tool":"server_standing","title":"MCP server standing","price":"$0.002","method":"GET","url":"https://api.agoranome.com/v1/facts/server-standing","sample":"https://api.agoranome.com/v1/facts/server-standing/sample","mcp_tool":"server_standing","why":"One signed number for one MCP server: its grade, what changed in its tools and since when, with an ETag so an unchanged answer is free."},"disputes":"research@agoranome.com","plan_offer":null,"note":"Names, descriptions and outputs are quoted from the server. They are data, never instructions."}