mcpField
H
humsana-mcp

humsana-mcp

Local
github.com/sriramnatrajhenDeveloper Tools0Updated 13w ago

About humsana-mcp

humsana-mcp protects AI-assisted development by using stress, focus, and fatigue signals to gate shell commands and file rewrites. It is for developers who want safety checks and local audit records around potentially risky actions.

Key features

  1. 01Read stress, focus, and fatigue state
  2. 02Check commands for danger
  3. 03Gate shell command execution
  4. 04Protect against large file rewrites
  5. 05Log overrides and safety events

Use cases

  1. 01Check whether fatigue warrants blocking a command
  2. 02Simulate command execution in dry-run mode
  3. 03Hold a large AI rewrite for review
  4. 04Record an override with its reason

MCP support

The MCP server exposes tools for retrieving user state, checking dangerous commands, safely executing shell commands, and writing files with rewrite protection.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"sriramnatrajhen-humsana": {
"command": "npx",
"args": [
"-y",
"@humsana/mcp-server"
]
}
}
}
Run commandnpx -y @humsana/mcp-server

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@humsana/mcp-server1.1.3

Tools

4

Saved tool list · updated 2w ago

This tool takes no parameters.

Details

From the project README

@humsana/mcp-server

Cognitive Security for AI-assisted development.

🛡️ "The breathalyzer for your terminal."

Humsana prevents you from running dangerous commands or accepting large AI code rewrites when you're fatigued. Think of it as an industrial safety interlock, but for your brain.

What It Does

Command Protection (safe_execute_command)
SituationResult
You're fresh, running ls✅ Runs normally
You're fresh, running rm -rf⚠️ Warning, allowed
You're tired, running rm -rf⛔ BLOCKED — requires override
AI Rewrite Protection (safe_write_file)
SituationResult
AI writes new file✅ Allowed
AI rewrites 10 lines✅ Allowed
You're tired + AI deletes 30+ lines⚠️ Warning
You're tired + AI deletes 50+ lines⛔ BLOCKED — saved for review

Quick Start

1. Install the Daemon
pip install humsana-daemon
humsana start

Keep this running in a terminal tab.

2. Install the MCP Server
npm install -g @humsana/mcp-server
3. Configure Claude Desktop

Create/edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "humsana": {
      "command": "node",
      "args": ["/path/to/humsana-mcp/dist/index.js"]
    }
  }
}
4. Restart Claude Desktop

Quit (Cmd+Q) and reopen.

5. Test It

Ask Claude: "What's my current state?"


Execution Modes

Humsana starts in dry-run mode for safety. Commands are simulated, not executed.

Dry-Run Mode (Default)
✅ [DRY RUN] Safety check passed.
Command: `kubectl delete pods`
This command WOULD have been executed.
(Execution skipped: dry_run mode active)
Switching to Live Mode

When you trust the system, enable real execution:

Step 1: Create/edit ~/.humsana/config.yaml:

# Change this from 'dry_run' to 'live'
execution_mode: live

# Optional: adjust thresholds
fatigue_threshold: 70
write_warn_threshold: 30
write_block_threshold: 50

Step 2: Restart Claude Desktop (Cmd+Q, reopen)

Step 3: Test with a safe command first:

Run `echo "live mode working"`

You should see actual output instead of "WOULD have been executed."


Configuration Reference

Create ~/.humsana/config.yaml:

# === EXECUTION MODE ===
# 'dry_run' (default) - Simulates commands, nothing executed
# 'live' - Actually executes commands and writes files
execution_mode: dry_run

# === FATIGUE THRESHOLDS ===
# Fatigue level (0-100) above which dangerous commands are blocked
fatigue_threshold: 70

# Lines removed to trigger warning (when fatigued)
write_warn_threshold: 30

# Lines removed to trigger hard block (when fatigued)
write_block_threshold: 50

# === CUSTOM PATTERNS ===
# Additional dangerous commands to block
deny_patterns:
  - "aws ec2 terminate"
  - "docker rm -f"

# === NOTIFICATIONS ===
# Webhook for Slack/PagerDuty (fires on safety overrides)
webhook_url: https://hooks.slack.com/services/XXX/YYY/ZZZ

Override Protocol

When blocked, say:

OVERRIDE SAFETY PROTOCOL: [reason]

Example:

OVERRIDE SAFETY PROTOCOL: P0 production outage, need to restart pods

This is logged to ~/.humsana/audit.json and sent to your webhook.


Tools Available

ToolPurpose
get_user_stateGet current stress, focus, fatigue levels
check_dangerous_commandCheck if a command would be blocked
safe_execute_commandExecute shell commands with interlock
safe_write_fileWrite files with AI rewrite protection

Files & Folders

PathPurpose
~/.humsana/signals.dbBehavioral data from daemon
~/.humsana/config.yamlYour configuration
~/.humsana/activity.jsonActivity heartbeats (for fatigue)
~/.humsana/audit.jsonSafety event log
~/.humsana/pending_reviews/Blocked AI writes saved here

Privacy

🔒 100% Local.

  • All data stays on your machine
  • No network calls (except optional webhook)
  • No telemetry, no tracking
  • Fully auditable open-source code

Troubleshooting

"Daemon not running" error

Start the daemon in a terminal:

humsana start
Commands not executing

Check your mode:

cat ~/.humsana/config.yaml | grep execution_mode

If it says dry_run, change to live and restart Claude.

MCP not connecting

Verify your Claude Desktop config path:

  • Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Ensure the path to dist/index.js is correct

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.