@humsana/mcp-server
Cognitive security for AI-assisted development, preventing dangerous commands and large AI code rewrites when fatigued.
README
@humsana/mcp-server
Cognitive Security for AI-assisted development.
š”ļø "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)
| Situation | Result |
|---|---|
You're fresh, running ls |
ā Runs normally |
You're fresh, running rm -rf |
ā ļø Warning, allowed |
You're tired, running rm -rf |
ā BLOCKED ā requires override |
AI Rewrite Protection (safe_write_file)
| Situation | Result |
|---|---|
| AI writes new file | ā Allowed |
| AI rewrites 10 lines | ā Allowed |
| You're tired + AI deletes 30+ lines | ā ļø Warning |
| You're tired + AI deletes 50+ lines | ā BLOCKED ā 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)
ā
[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
| Tool | Purpose |
|---|---|
get_user_state |
Get current stress, focus, fatigue levels |
check_dangerous_command |
Check if a command would be blocked |
safe_execute_command |
Execute shell commands with interlock |
safe_write_file |
Write files with AI rewrite protection |
Files & Folders
| Path | Purpose |
|---|---|
~/.humsana/signals.db |
Behavioral data from daemon |
~/.humsana/config.yaml |
Your configuration |
~/.humsana/activity.json |
Activity heartbeats (for fatigue) |
~/.humsana/audit.json |
Safety event log |
~/.humsana/pending_reviews/ |
Blocked AI writes saved here |
Privacy
š 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.jsis correct
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.