🛡️ Node9

What did your AI agent actually do? Find out, and stop the dangerous stuff.

What node9 scan shows on a real machine

This is my own machine — 30 days while building Node9. Score 25/100, 5 credential files an AI agent could reach right now.

🛡  Node9 Scan  ·  21 sessions  ·  8,114 tool calls  ·  Apr 6 – May 1, 2026

Security Score: 25/100  ·  Critical
$3,789 AI spend  ·  62 risky operations

🔑  14   credential leak     (Bearer Token ×4, GCP API Key ×4, JWT ×2)
🛑  15   would have blocked  (force-push ×5, read-ssh ×4, read-aws ×4)
🔁  193  agent loops         (18% wasted  ·  ~$6.51)
👁  33   flagged for review  (git-destructive ×19, rm ×9, sudo ×2)

🔭  Blast radius             ssh × gcp × npm × other (5 exposures)

→  npx node9-ai scan         run this on your machine

Run it on yours — npx node9-ai scan finishes in ~10 seconds and runs entirely local. Nothing uploads. The full breakdown with every tool call, file path, and timestamp is node9 scan (default mode). For a browser dashboard view, run node9 daemon start --openui.

What Node9 does

• 🛑 Block dangerous AI actions before they run — rm -rf, git push --force, DROP TABLE, credential reads, curl | bash
• 🔍 Scan what your AI agent has already been doing — loops, leaked secrets, blocked operations across every session
• 🔑 Catch credential leaks — AWS keys, GitHub tokens, JWTs, GCP API keys, PEM private keys flagged in tool arguments, file contents Claude reads back, and shell config files
• 🔭 Map your blast radius — every SSH key, AWS credential, and .env file an AI agent on this machine could reach right now

Works with Claude Code · Cursor · Codex · Gemini CLI · any MCP server.

How is this different from gitleaks / Snyk / TruffleHog?

Those scan repositories for credentials. Node9 scans AI agent session history — what your AI ran, what it read, what credentials passed through tool calls. Different surface area.

Node9 catches things gitleaks can't:

• Credentials the AI read but never committed
• Agent edit loops that burn tokens on retries
• Dangerous shell commands the AI ran without confirmation
• Blast radius — which credential files an AI agent on this machine could reach right now

Run gitleaks for committed code. Run Node9 for AI session history.

Install

# macOS / Linux
brew tap node9-ai/node9 && brew install node9

# or via npm (any platform)
npm install -g node9-ai

node9 init       # auto-wires Claude Code, Gemini CLI, Cursor, Codex, MCP servers
node9 doctor     # verify everything is wired correctly

That's it — future agent sessions are protected.

Shields — expert policy in one command

Each shield is a curated rule set for a service or domain. Enable only what you need.

node9 shield list    # show all shields + status

Always on — no config needed

• Git — blocks git push --force, git reset --hard, git clean -fd
• SQL — blocks DELETE / UPDATE without WHERE, DROP TABLE, TRUNCATE
• Shell — blocks curl | bash, unauthorized sudo
• DLP — blocks AWS keys, GitHub tokens, Stripe keys, PEM private keys in any tool argument, file Claude reads, or shell config (~/.zshrc, ~/.bashrc)
• Response DLP — background scanner reads Claude's conversation history and alerts you if Claude wrote a secret in its response text (not just executed one). Gemini / Codex coverage coming.
• Auto-undo — git snapshot before every AI file edit → node9 undo to revert
• Skills pinning — SHA-256 verification of installed Claude skills / plugins between sessions

MCP gateway — protect any MCP server

Wrap any MCP server transparently. The agent sees the same server — Node9 intercepts every tool call.

{
  "mcpServers": {
    "postgres": {
      "command": "node9",
      "args": ["mcp", "--upstream", "npx -y @modelcontextprotocol/server-postgres postgresql://..."]
    }
  }
}

Or just run node9 init — it wraps your existing MCP servers automatically.

node9 mcp pin list                # show all pinned servers and hashes
node9 mcp pin update <serverKey>  # remove pin, re-pin on next connection
node9 mcp pin reset               # clear all pins

Observability — five views

Every tool call is recorded — command, arguments, decision, cost. See what your agent did, five ways:

Plus a live HUD in your Claude Code statusline:

🛡 node9 | standard | [bash-safe] | ✅ 12 allowed  🛑 2 blocked  🚨 0 dlp | ~$0.43
📊 claude-opus-4-6 | ctx [████████░░░] 54% | 5h [██░░░░░░░░] 12% | 7d [█░░░░░░░] 7%
🗂 2 CLAUDE.md | 8 rules | 3 MCPs | 4 hooks

And a browser dashboard that auto-opens after node9 scan — History Audit modal with full drill-down, per-agent breakdown, loop-cost estimate, and live status strip.

Reading the data — what the numbers mean

Node9 surfaces the signal. Here are the patterns worth knowing:

These are starting points, not verdicts. One-off signals are normal; persistent patterns are what you act on.

Python SDK — govern any Python agent

from node9 import configure, protect

configure(agent_name="my-agent", policy="require_approval")

@protect("bash")
def run_command(cmd: str) -> str:
    ...

Python SDK → · CI code review agent example →

Under the hood

• Scan reads raw agent history from ~/.claude/projects/, ~/.gemini/tmp/, ~/.codex/sessions/ — no API calls, fully offline
• Runtime wires PreToolUse hooks into Claude Code, Gemini CLI, and Codex — hooks write to ~/.node9/audit.log atomically
• MCP gateway is a stdio proxy; intercepts tools/list + tools/call JSON-RPC, forwards the rest
• Policy engine uses mvdan-sh for bash AST analysis — defeats obfuscation via backslash escaping, variable substitution, eval of remote download
• Shadow repo for auto-undo lives at ~/.node9/snapshots/<hash16>/ — never touches your .git

📖 Full docs

Everything else — config reference, smart rules, stateful rules, trusted hosts, approval modes, Slack integration, CLI reference — is at node9.ai/docs.

Related projects

• node9-python — Python SDK for governed agents
• node9-pr-agent — GitHub Action that reviews PRs through Node9 (reference implementation of a governed agent)

Enterprise

Node9 Pro adds governance locking, SAML/SSO, central audit export, and VPC deployment. See node9.ai.

_{Built with ☕ and healthy paranoia.}