Nefesh

@tomstuhl

Visit Server

21 days ago

Real-time human state awareness for AI agents. Fuses cardiovascular, vocal, visual, and textual signals into a unified stress score (0-100). MCP + A2A native. 7 tools, 4 A2A skills. Closed-loop adaptation feedback. Free tier available.

Overview Tools Comments

Overview

Nefesh MCP Server

A Model Context Protocol server that gives AI agents real-time awareness of human physiological state.

What it does

Send sensor data (heart rate, voice, facial expression, text sentiment), get back a unified state with a machine-readable action your agent can follow directly. Zero prompt engineering required.

On the 2nd+ call, the response includes adaptation_effectiveness — telling your agent whether its previous approach actually worked. A closed-loop feedback system for self-improving agents.

Setup

Option A: Connect first, get a key through your agent (fastest)

Add the config without an API key — your agent will get one automatically.

{
  "mcpServers": {
    "nefesh": {
      "url": "https://mcp.nefesh.ai/mcp"
    }
  }
}

Then ask your agent:

"Connect to Nefesh and get me a free API key for name@example.com"

The agent calls request_api_key → you click one email link → the agent picks up the key. No signup form, no manual copy-paste. After that, add the key to your config for future sessions:

{
  "mcpServers": {
    "nefesh": {
      "url": "https://mcp.nefesh.ai/mcp",
      "headers": {
        "X-Nefesh-Key": "nfsh_free_..."
      }
    }
  }
}

Option B: Get a key first, then connect

{
  "mcpServers": {
    "nefesh": {
      "url": "https://mcp.nefesh.ai/mcp",
      "headers": {
        "X-Nefesh-Key": "YOUR_API_KEY"
      }
    }
  }
}

Agent-specific config files

Agent	Config file
Cursor	`~/.cursor/mcp.json`
Windsurf	`~/.codeium/windsurf/mcp_config.json`
Claude Desktop	`~/Library/Application Support/Claude/claude_desktop_config.json`
Claude Code	`.mcp.json` (project root)
VS Code (Copilot)	`.vscode/mcp.json` or `~/Library/Application Support/Code/User/mcp.json`
Cline	`cline_mcp_settings.json` (via UI: "Configure MCP Servers")
Continue.dev	`.continue/config.yaml`
Roo Code	`.roo/mcp.json`
Amazon Q	`~/.aws/amazonq/mcp.json`
JetBrains IDEs	Settings > Tools > MCP Server
Zed	`~/.config/zed/settings.json` (uses `context_servers`)
OpenAI Codex CLI	`~/.codex/config.toml`
Goose CLI	`~/.config/goose/config.yaml`
ChatGPT Desktop	Settings > Apps > Add MCP Server (UI)
Gemini CLI	Settings (UI)
Augment	Settings Panel (UI)
Replit	Integrations Page (web UI)
LibreChat	`librechat.yaml` (self-hosted)

VS Code (Copilot) — uses servers instead of mcpServers

{
  "servers": {
    "nefesh": {
      "type": "http",
      "url": "https://mcp.nefesh.ai/mcp",
      "headers": {
        "X-Nefesh-Key": "<YOUR_API_KEY>"
      }
    }
  }
}

Zed — uses context_servers in settings.json

{
  "context_servers": {
    "nefesh": {
      "settings": {
        "url": "https://mcp.nefesh.ai/mcp",
        "headers": {
          "X-Nefesh-Key": "<YOUR_API_KEY>"
        }
      }
    }
  }
}

OpenAI Codex CLI — uses TOML in ~/.codex/config.toml

[mcp_servers.nefesh]
url = "https://mcp.nefesh.ai/mcp"

Continue.dev — uses YAML in .continue/config.yaml

mcpServers:
  - name: nefesh
    type: streamable-http
    url: https://mcp.nefesh.ai/mcp

All agents connect via Streamable HTTP — no local installation required.

Tools

Tool	Auth required	Description
`request_api_key`	No	Request a free API key by email
`check_api_key_status`	No	Poll for API key activation after email click
`get_human_state`	Yes	Get current stress state, score, confidence, and suggested action
`ingest`	Yes	Send biometric signals, get unified state back
`get_trigger_memory`	Yes	Get psychological trigger profile for a subject
`get_session_history`	Yes	Get state history over time
`delete_subject`	Yes	Delete all stored data for a subject (GDPR)

How self-provisioning works

Your AI agent can get a free API key autonomously. You only click one email link.

Agent calls request_api_key(email) — no API key needed for this call
You receive a verification email and click the link
Agent polls check_api_key_status(request_id) every 10 seconds
Once verified, the agent receives the API key and can use all other tools

Free tier: 1,000 calls/month, all signal types, 10 req/min. No credit card.

Quick test

After adding the config, ask your AI agent:

"What tools do you have from Nefesh?"

It should list the 7 tools above.

Pricing

Plan	Price	API Calls
Free	$0	1,000/month, no credit card
Solo	$25/month	50,000/month
Enterprise	Custom	Custom SLA

Documentation

Privacy

No video or audio uploads — edge processing runs client-side
No PII stored
GDPR/BIPA compliant — cascading deletion via delete_subject
Not a medical device — for contextual AI adaptation only

License

MIT — see LICENSE.

Try in Playground

Server Config

{
  "mcpServers": {
    "nefesh": {
      "url": "https://mcp.nefesh.ai/mcp",
      "headers": {
        "X-Nefesh-Key": "<YOUR_API_KEY>"
      }
    }
  }
}

Build with ShipAny.