Tracks human stress from biometric and communication signals, then returns actions and feedback for adaptive AI interactions.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent โ or use 1-click editor setup below.
๐ก Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Nefesh โ Real Time Human State Awareness.
request_api_keyRequest a free API key. You MUST ask the user for their real email first. Do not invent or guess emails. The user receives a verification link they must click. Poll with `check_api_key_status` until ready.
check_api_key_statusPoll for API key activation using the same email the user provided. Returns `pending` or `ready` with API key.
get_human_stateGet stress state (0-100), `suggested_action` (maintain/simplify/de-escalate/pause), and `adaptation_effectiveness` โ a closed-loop showing whether your previous action reduced stress.
ingestSend biometric signals (heart rate, HRV, voice tone, expression, sentiment, 30+ fields) and get unified state back. Include `subject_id` for trigger memory.
get_trigger_memoryGet psychological trigger profile โ which topics cause stress (active) and which have been resolved over time.
get_session_historyGet timestamped state history with trend (rising/falling/stable).
Nefesh โ Real-time Human State Awareness gives MCP-compatible agents access to a unified view of human state. It accepts signals such as heart rate, heart-rate variability, voice tone, facial expression, and text sentiment, then returns a stress score from 0 to 100 along with a recommended response such as maintaining, simplifying, de-escalating, or pausing.
The service also reports whether a previous agent action appears to have reduced stress. On later calls in a session, the response can include the previous action, earlier and current scores, the change between them, and an effectiveness result. This lets an agent compare its interventions instead of reacting only to the latest reading.
The hosted MCP endpoint is https://mcp.nefesh.ai/mcp and uses Streamable HTTP, so the client does not need a local server installation. An authenticated client can call ingest with available biometric or communication signals and receive the combined state. Supplying a subject_id enables trigger-memory behavior for that subject.
get_human_state retrieves the current stress state and adaptation feedback. get_session_history returns timestamped states with a rising, falling, or stable trend. get_trigger_memory reports topics associated with active stress responses and topics that have been resolved over time.
Nefesh โ Real-time Human State Awareness also exposes an A2A interface at https://mcp.nefesh.ai/a2a, using JSON-RPC 2.0. The A2A agent card is available at /.well-known/agent-card.json, and the same API-key authentication applies to both protocols.
Connect the client to the hosted MCP URL with no key to begin the self-provisioning flow, or add an existing key in the X-Nefesh-Key header. To request a key through the server, the agent must ask for the user's real, accessible email address. The user then clicks the verification link, and the agent polls check_api_key_status until the key is ready. Disposable addresses are blocked.
Alternatively, obtain a key through the Nefesh signup page and place it in the client configuration. The documented free tier provides 1,000 calls per month, supports all signal types, limits traffic to 10 requests per minute, and does not require a credit card.
Configuration examples and client-specific locations are documented for Cursor, Windsurf, Claude Desktop, Claude Code, VS Code, Cline, Continue, Roo Code, JetBrains IDEs, Zed, OpenAI Codex CLI, and Gemini CLI. These clients connect to the remote endpoint rather than installing a local package.
request_api_key: starts free-key provisioning after receiving the user's real email.check_api_key_status: checks whether email verification is complete and returns a pending or ready result.get_human_state: returns stress, a suggested action, and adaptation effectiveness.ingest: submits 30 or more supported signal fields and returns the unified state.get_trigger_memory: retrieves active and resolved psychological trigger information.get_session_history: returns state history with a trend indicator.Nefesh โ Real-time Human State Awareness requires user verification for self-service API-key creation; an agent must not invent or guess an email address. Authenticated state and signal tools require an API key. The service is designed to process supplied signals, so its output depends on the data sent by the client.
The free plan has a monthly call allowance and a rate limit. The material identifies the service as GDPR compliant, but it does not specify retention periods, regional hosting, data deletion procedures, or the exact set of supported signal fields. Review those details before using it for sensitive production workloads.
Factual signals from GitHub, npm, and our automated checks โ not a rating.
No reviews yet โ be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/nefesh-real-time-human-state-awareness)<a href="https://allmcps.com/mcp/nefesh-real-time-human-state-awareness"><img src="https://allmcps.com/api/badge/nefesh-real-time-human-state-awareness?style=directory" alt="Nefesh โ Real Time Human State Awareness on AllMCPs" /></a>