Nefesh

by nefesh-ai

234 downloads

Not rated

GitHub

About

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.

Details

Author: nefesh-ai
Downloads: 234
Categories: Other, AI, Infrastructure

- Seven tools including ingest, get_human_state, and delete_subject
- Self‑provisioning: agent fetches API key autonomously after email verification
- Returns adaptation_effectiveness on second+ call for closed‑loop feedback
- Free tier: 1,000 calls/month with no credit card
- No video/audio uploads; edge processing runs client‑side
- GDPR/BIPA compliant with delete_subject for cascading deletion

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name Nefesh

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

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

JSON

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

JSON

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

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

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

JSON

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

JSON

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

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

From the repository

Add the server URL to your MCP client config (e.g., ~/.cursor/mcp.json). Use Option A: connect without an API key and ask your agent to call request_api_key — after clicking a verification email, the agent retrieves the key automatically. Option B: sign up at nefesh.ai/signup for a free key (1,000 calls/month) and include it in the config headers. All agents connect via Streamable HTTP — no local installation required.

`get_human_state`

Get current unified human state for a session. Returns stress level, active signals, confidence, and a default LLM behavior recommendation. Call before generating important responses. Not a medical device.

`ingest`

Send human signals from any sensor, get unified state back. session_id + timestamp + at least one signal required. Heart rate, glucose, EEG, voice tone, facial expression — send what you have. Not a medical device.

`get_history`

Get state history over time for a session. Returns timestamped state snapshots from the last N minutes. Useful for tracking stress trends. Not a medical device.

`delete_subject`

GDPR-compliant deletion of all data for a subject. Cascading delete: removes all sessions and stored signals for the given subject_id. Irreversible. Not a medical device.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

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

McpServers

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

AModel Context Protocoland Agent-to-Agent (A2A)server that gives AI agents real-time awareness of human physiological state.

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 includesadaptation_effectiveness— telling your agent whether its previous approach actually worked. A closed-loop feedback system for self-improving agents.

Most APIs give you a state. Nefesh tells you whether your reaction to that state actually worked.

On the 2nd+ call within a session, every response includes:

{ "state": "focused", "stress_score": 45, "suggested_action": "simplify_and_focus", "adaptation_effectiveness": { "previous_action": "de-escalate_and_shorten", "previous_score": 68, "current_score": 45, "stress_delta": -23, "effective": true } }

Your agent can readeffective: trueand know its previous de-escalation worked. Ifeffective: false, the agent adjusts its strategy. No other human-state system provides this feedback loop.

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

Add the configwithout an API key— your agent will get one automatically.

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

"Get me a free Nefesh API key using my email address"

The agent callsrequest_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_..." } } } }

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

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

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

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

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

All agents connect viaStreamable HTTP— no local installation required.

A2A Integration (Agent-to-Agent Protocol v1.0)

Nefesh is also available as an A2A-compatible agent. While MCP handles tool-calling (your agent calls Nefesh), A2A enables agent-collaboration — other AI agents can communicate with Nefesh as a peer.

Agent Card:/.well-known/agent-card.json

A2A Endpoint:POST https://mcp.nefesh.ai/a2a(JSON-RPC 2.0)

Same authentication as MCP —X-Nefesh-Keyheader orAuthorization: Bearertoken. Free tier works on both protocols.

Source:nefesh-ai/nefesh-a2a· Docs:nefesh.ai/docs/a2a

Your AI agent can get a free API key autonomously. You only click one email link.
- Agent asks you: "What is your email address?"
- Agent callsrequest_api_key(your_real_email). No API key needed for this call.
- You receive a verification email and click the link
- Agent pollscheck_api_key_status(your_real_email)every 10 seconds
- Once verified, the agent receives the API key and can use all other tools

Important:The agent must use your real, accessible email address. Disposable emails are blocked. The verification link must be clicked by you to activate the key.

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

After adding the config, ask your AI agent:

"What tools do you have from Nefesh?"

Prefer the terminal over MCP? Use the Nefesh CLI (10-32x lower token cost than MCP for AI agents):

npm install -g @nefesh/cli nefesh ingest --session test --heart-rate 72 --tone calm nefesh state test --json

Want the AI to adapt automatically? Use the Nefesh Cognitive Compute Router. Change your LLM base URL togateway.nefesh.aiand the gateway adjusts system prompt and temperature based on biometric state. Three modes: OpenAI-compatible (/v1/chat/completions), Anthropic passthrough (/v1/messages), and Unified Anthropic for any backend. Zero code changes.

Nefesh implements and maintains the Human State Protocol, an open specification for exchanging human physiological state between AI systems. HSP defines a standard JSON format for stress scores, behavioral recommendations, and adaptation feedback so any agent can produce or consume human state data interoperably. Apache 2.0.

GitHub:nefesh-ai/human-state-protocol· Docs:nefesh.ai/docs/hsp

- Full API Reference
- Quick Start
- State Mapping
- MCP Server·Source
- A2A Server·Source
- Cognitive Compute Router (Gateway)·Source
- CLI·Source
- Human State Protocol (HSP)·Source
- A2A Agent Card
- A2A Protocol Spec

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

Monitor air quality with Airthings devices.

AI-powered industrial fault diagnosis MCP server. 313 fault codes across Allen-Bradley, Siemens, ABB, Mitsubishi, Fanuc. 8 diagnostic tools for Claude Code.

Real-time human state awareness for AI agents. Fuses biometric signals into a unified stress score (0-100) via Streamable HTTP.

AI-powered wellbeing insights with real-time benchmarks and alerts.

A 3D Printing MCP server that allows for querying for live state, webcam snapshots, and 3D printer control.

AI coach for running, cycling, triathlon

Enforces organisational AI usage policies at the agent layer — blocks prohibited model calls, enforces data residency rules, logs policy violations, and ensures AI governance policies are machine-executable.

AI-powered cycling training coach: personalized training plans, daily workouts, nutrition, strength training, fitness metrics (FTP, VO2Max), and Strava, Garmin, Wahoo, MyWhoosh, and Rouvy integrations.

Behavioral trust layer for the AI agent economy. Check MCP server reliability scores, report interactions, detect anomalies, and discover the most trusted servers. 8 tools, free, real-time.

Behavioral trust scoring for 14,820+ MCP servers. Check reliability, latency, and success rates before tool calls.

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

Nefesh

About

Details

Jump to

Setting up with Highlight

Setting up with Cursor

JSON

JSON

JSON

Setting up with Claude Desktop

JSON

JSON

JSON

Setting up with Windsurf

JSON

JSON

JSON

Setting up with Cline

JSON

JSON

JSON

Setting up with Goose

JSON

JSON

JSON

From the repository

`get_human_state`

`ingest`

`get_history`

`delete_subject`

Claude Desktop / Cursor

McpServers

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

A2A Integration (Agent-to-Agent Protocol v1.0)

Install

About

Details

Jump to

Setting up with Highlight

From the repository

get_human_state

ingest

get_history

delete_subject

Claude Desktop / Cursor

McpServers

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

A2A Integration (Agent-to-Agent Protocol v1.0)

Install

More like this

Sequential Thinking

Filesystem

EverArt

Google Drive

Context 7

Reactive Resume

`get_human_state`

`ingest`

`get_history`

`delete_subject`