Nefesh — Real-Time Human State Awareness for AI
Server Details
Fuses biometric signals into a stress score (0-100) for AI adaptation. MCP + A2A native.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- nefesh-ai/nefesh-mcp-server
- GitHub Stars
- 0
- Server Listing
- nefesh
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 7 tools
Each tool has a distinct role: two are sequential auth steps, one ingests signals, three retrieve different slices of state (current, historical, cross-session triggers), and one deletes subject data. The only apparent overlap is that ingest also returns state fields, but its required signal inputs clearly separate it from get_human_state.
Almost all names follow a snake_case verb_noun or verb_noun_noun pattern (get_human_state, get_session_history, get_trigger_memory, delete_subject, request_api_key, check_api_key_status). The lone single-verb name 'ingest' is a minor deviation from that pattern but remains clear.
Seven tools is well-scoped for this domain, covering auth, signal ingestion, current state, session history, trigger memory, and subject deletion without obvious bloat. Each tool earns its place and the set stays lightweight.
The surface covers the core lifecycle: authorize, ingest signals, read current state, inspect history, review cross-session triggers, and delete a subject. Minor gaps include no session-level deletion or subject listing, but agents can likely work around these for the stated purpose.
Available Tools
7 toolscheck_api_key_statusAInspect
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.
Inputs: request_id (required).
delete_subjectADestructiveIdempotentInspect
Permanently delete all sessions and trigger memory for a subject.
Irreversible. Only call when the user explicitly requests this deletion.
Inputs: subject_id (required).
get_human_stateAInspect
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.
Inputs: session_id (required).
get_session_historyAInspect
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.
Inputs: session_id (required), minutes.
get_trigger_memoryAInspect
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.
Inputs: subject_id (required).
ingestAInspect
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.
Inputs: timestamp (required), session_id (required), eda, gaze, +33 more.
request_api_keyAInspect
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.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
On-device human sensing for AI: EDNA ID continuity and live human context via MCP.
Adaptive running coach MCP server — training data, plans, and recovery for AI assistants.
Connect your wearables, rings and training apps, then ask your AI about your own health data.
Intelligence subscription protocol for AI agents. Scored, filtered AI intelligence signals via MCP.
Related MCP Servers
- AlicenseAqualityDmaintenanceReal-time human state awareness for AI agents. Fuses cardiovascular, vocal, visual, and textual signals into a unified stress score (0-100). Streamable HTTP transport with 4 tools: ingest_signal, get_human_state, get_history, delete_subject.6MIT
- AlicenseNot gradedqualityBmaintenanceEnables computational neuroendocrine modeling of sAA biomarker timeseries to compute surge deltas, reactivity ratios, clearance velocity, and a 0–100 autonomic stress resilience index with breathing-protocol guidance.7MIT
- FlicenseNot gradedqualityNot gradedmaintenanceEnables users to evaluate biometric sleep and HRV recovery data, calculate a cognitive readiness score, and automatically reallocate demanding work blocks based on current capacity.-
- AlicenseNot gradedqualityBmaintenanceEnables ambient multimodal clinical triage by fusing wearable ECG/PPG and acoustic distress signals, applying deterministic Manchester Triage safety governance, and orchestrating emergency actions such as E911 dispatch, smart-lock access, and CPR coaching through MCP tools and resources.Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.