Nefesh — Real Time Human State Awareness for AI vs Email MCP
In-depth architectural comparison of the Nefesh — Real Time Human State Awareness for AI and Email MCP MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Nefesh — Real Time Human State Awareness for AI
Communication · Remote HTTP/SSE
Quality: 47/100 (Fair) | Auth: No auth required
Email MCP
Communication · Local stdio
Quality: 65/100 (Great) | Auth: other
Verdict Summary: Choose Nefesh — Real Time Human State Awareness for AI if you need specialized Communication tools running via a hosted cloud SSE transport. Choose Email MCP if your workspace requires Communication integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Nefesh — Real Time Human State Awareness for AI when:
You need dedicated capabilities in the Communication domain.
You prefer remote streaming HTTP/SSE transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Fuses biometric signals into a stress score (0-100) for AI adaptation. MCP + A2A native.
IMAP/SMTP email MCP server with 42 tools for reading, searching, sending, scheduling, and managing emails across multiple accounts. Supports IMAP IDLE push, AI triage, desktop notifications, and auto-detects providers like Gmail, Outlook, and iCloud.
Nefesh — Real Time Human State Awareness for AI Tools (6)
request_api_key
Request 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_status
Poll for API key activation using the same email the user provided. Returns `pending` or `ready` with API key.
get_human_state
Get stress state (0-100), `suggested_action` (maintain/simplify/de-escalate/pause), and `adaptation_effectiveness` — a closed-loop showing whether your previous action reduced stress.
ingest
Send biometric signals (heart rate, HRV, voice tone, expression, sentiment, 30+ fields) and get unified state back. Include `subject_id` for trigger memory.
get_trigger_memory
Get psychological trigger profile — which topics cause stress (active) and which have been resolved over time.
get_session_history
Get timestamped state history with trend (rising/falling/stable).
Email MCP Tools (47)
list_accounts
List all configured email accounts
list_mailboxes
List folders with unread counts and special-use flags
list_emails
Paginated email listing with date, sender, subject, and flag filters
get_email
Read full email content with attachment metadata
get_emails
Fetch full content of multiple emails in a single call (max 20)
get_email_status
Get read/flag/label state of an email without fetching the body
search_emails
Search by keyword across subject, sender, and body
download_attachment
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Nefesh — Real Time Human State Awareness for AI Configuration
Nefesh — Real Time Human State Awareness for AI is categorized under Communication and uses a remote streaming HTTP/SSE transport. In contrast, Email MCP belongs to Communication using local stdio subprocess. Select Nefesh — Real Time Human State Awareness for AI when you need capabilities focused on communication and Email MCP when you require tools for communication.