6 tools from the Human State MCP Server, categorised by risk level.
View the Human State policy →check_api_key_status Poll for API key activation after calling request_api_key. No existing API key needed.
Returns status: 'pending' (keep polling) or 'ready' (in... 2/5 get_human_state Get current unified human state for a session. Call this before generating important responses.
Returns:
- state: calm | relaxed | focused... get_session_history Get state history for a session over time.
Returns timestamped datapoints with stress_score, state, and heart_rate for each observation.
I... get_trigger_memory Retrieve psychological trigger profile for a subject.
Returns which conversation topics consistently cause stress (active triggers) and which ... request_api_key Request a free Nefesh API key. No existing API key needed for this call.
Flow: call this → developer clicks email link → poll check_api_key_st... 2/5 The Human State MCP server exposes 6 tools across 2 categories: Read, Execute.
Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Human State server.
Human State tools are categorised as Read (5), Execute (1). Each category has a recommended default policy.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept