@node9/proxy

🛡️ Node9

What did your AI agent actually do? Find out.

Node9 sits between your AI agent and the tools it can use — discover what it's already been doing, protect against risky actions in real time, and review what happened over any time window.

Works with Claude Code · Codex CLI · Antigravity (agy) · GitHub Copilot CLI · Gemini CLI · Cursor · Windsurf · VSCode · Claude Desktop · Opencode · Pi · Hermes Agent · any MCP server.

What Node9 does

• 🔍 Discover — scan every past AI session for credential leaks, agent loops, blocked operations, and every secret on disk an agent could reach right now
• 🛡 Protect — review or block risky commands before they run — rm -rf, git push --force, DROP TABLE, credential reads, curl | bash, AWS/GitHub/Stripe key leaks
• 📊 Review — period-windowed report (today / week / month / 90 days) — cost per agent, top tools, shields fired, blast radius

Retrospective scan

This is my own machine — 90 days while building Node9. Score 25/100, 5 credential files an AI agent could reach right now.

npx node9-ai scan   # before installation, runs in ~10s, nothing uploads
node9 scan          # after installation, same output

Security posture scorecard

node9 posture grades how exposed this machine is to a compromised agent — isolation, egress, secrets on disk, supply chain, privilege — and hands you the exact command to fix each finding.

node9 posture          # scorecard with the #1 risk and a fix for every finding
node9 posture --ship   # send a redacted snapshot to your node9 dashboard (fleet view)

Findings are grouped by who can fix them: 🔒 the ones node9 reduces (just run the command) and 🧱 the ones only you can. Each carries a plain-language what / why / who and a real remediation — e.g. the "agent runs unsandboxed on the host" finding points straight at node9 sandbox run (below).

🛡️  Node9 Posture — agent on this host        Score: 100/100  (Good)
  2 advisories below don't affect the score — OS-level exposure, yours to weigh.

  🟢 node9 is already protecting you
  ✅ Secrets        node9 DLP is blocking this
  ✅ Egress         node9 egress is approval-gating this
  ✅ Approval gate  node9 is blocking this
  ✅ Privilege      node9 is approval-gating this

  🔒 node9 reduces these — run the command, the rest is yours
  ⚠️  Isolation     Running directly on the host — no container
                   The agent runs loose on your whole machine, not in a sandbox.
                   → node9 sandbox run <agent>   — jail it: kernel egress + scoped mounts + node9 inside
                   → node9 shield enable project-jail   — or shrink the blast radius, keep host access
  ⚠️  Network exposure  4 services on 0.0.0.0 (node :3000/:4000, PostgreSQL :5432, Redis :6379)
                   Reachable from your whole network, not just this laptop.
                   → node9 shield enable postgres|redis   — node9 blocks DROP TABLE / FLUSHALL
                   → bind to 127.0.0.1 / firewall the port   (your part)

  ✅ Supply chain   no issues found
  ✅ Coverage       no issues found

  Track this across your fleet & keep it green → node9.ai

Scan a repo — agent-CI security

node9 scan-repo checks any repo (or a local folder) for ways an AI agent wired into GitHub Actions could be hijacked by an outsider — injectable workflows, agent-reachable secrets, unpinned MCP servers, over-broad agent config, and poisoned instruction files. Static and parse-only: it reads only committed config, never executes repo code. No install or token needed for public repos.

npx node9-ai scan-repo <owner/repo>   # any public repo, no install
node9 scan-repo .                      # a local checkout — no network
node9 scan-repo <owner/repo> --json    # machine-readable

🛡️  node9 scan-repo · node9-ai/agent-security-demo · ⚠️ agent-security risk found
   inspected 2 config file(s), 2 finding(s)

🔴 CRITICAL  Injectable agent workflow — untrusted input reaches a tool-using agent with secrets
   .github/workflows/vulnerable-example.yml · CI-2
     • runs with base-repo secrets (pull_request_target)
     • checks out the untrusted PR head into the workspace root
     • allowed_non_write_users: "*" — any user can trigger the agent
     • no effective actor gate

🔴 CRITICAL  Exfiltratable secrets reachable by an injectable agent
   .github/workflows/vulnerable-example.yml · CI-4
     • agent has arbitrary shell (bare Bash) → can read env and exfiltrate

What it checks:

Check	Flags
CI-1	committed agent config that pre-authorizes broad tools or runs remote hooks
CI-2	injectable agent workflows — an outsider can trigger the agent and hijack it
CI-3	unpinned / @latest MCP servers or inline credentials (supply chain)
CI-4	secrets an injected agent could exfiltrate
CI-6	poisoned or dangerous instructions in CLAUDE.md / AGENTS.md / skills

Gate every PR — the same engine as a GitHub Action, so a hijackable config can't get merged:

# .github/workflows/agent-security.yml
- uses: node9-ai/agent-security-action@v1
  with:
    fail-on: high # or 'never' to just comment

Marketplace: node9 Agent Security Check

Live monitoring

node9 monitor opens an interactive terminal dashboard with two views:

• [1] Realtime — live activity, approvals, security alerts, current risk score
• [2] Report — period-windowed summary: cost, top tools, shields fired, blast radius

Report

Press [2] in monitor for a period-windowed summary. Toggle the window with [T]oday · [W]eek · [M]onth · [N]inety — same panels as the scan above, driven by your post-install audit log.

node9 monitor              # press [2] for Report view
node9 report --period 7d   # CLI form, no TUI

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 all detected agents + MCP servers
node9 login      # connect this machine to your workspace (approve it in the browser)
node9 doctor     # verify everything is wired and reporting

Requires Node.js 18+.

init on its own gives you full local enforcement: rules, shields, DLP and approvals all work offline, on this machine.

login is what puts the machine on your dashboard. It prints a code, opens the browser, and you approve the machine there; if you don't have an account yet, signing up mid-flow returns you to the same approval with the code intact. Until you run it, everything is enforced locally but nothing reaches Mission Control, so the dashboard stays empty.

node9 logout disconnects a machine again. It revokes that machine's key; local enforcement keeps running.

Shields — curated rule packs

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

Shield	What it catches	Enable
project-jail	Blocks reads of ~/.ssh, ~/.aws, .env, credentials via Bash and Read tool	node9 shield enable project-jail
bash-safe	curl | bash, rm -rf /, disk overwrite, eval of remote	node9 shield enable bash-safe
postgres	DROP TABLE, TRUNCATE, DROP COLUMN, DELETE without WHERE	node9 shield enable postgres
mongodb	dropDatabase, drop(), deleteMany({}), index drops	node9 shield enable mongodb
redis	FLUSHALL, FLUSHDB, CONFIG SET on a live server	node9 shield enable redis
aws	S3 delete, EC2 terminate, IAM changes, RDS destroy	node9 shield enable aws
k8s	namespace delete, helm uninstall, cluster role wipes	node9 shield enable k8s
docker	system prune, volume prune, rm -f containers	node9 shield enable docker
github	gh repo delete, remote branch deletion, settings changes	node9 shield enable github
filesystem	chmod 777, writes under /etc/, /boot/, /usr/	node9 shield enable filesystem
mcp-tool-gating	unapproved MCP tools silently activating new capabilities	node9 shield enable mcp-tool-gating

node9 shield list    # show all shields + status

Always on — no config needed

• Git — catches git push --force, git reset --hard, git clean -fd
• SQL — catches DELETE / UPDATE without WHERE, DROP TABLE, TRUNCATE
• Shell — catches curl | bash, unauthorized sudo
• DLP — flags AWS keys, GitHub tokens, Stripe keys, PEM private keys in any tool argument, file contents, 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
• Skills pinning — SHA-256 verification of installed Claude skills / plugins between sessions

Review prompts — approve inline, in your agent

When node9 flags an action for review (e.g. git push --force, a DROP TABLE), the approve/deny prompt renders inline in the agent conversation — no frozen session, no separate terminal, no hook-timeout race. node9 still runs the full evaluator and makes the decision; only the prompt surface moves to the agent.

• On by default for Claude Code and GitHub Copilot CLI — the agents whose hook contract honors a native ask. Every other agent (Codex, Gemini, Antigravity, Hermes, Cursor, OpenCode, Pi) uses node9's own approver.
• Control it with reviewChannel in ~/.node9/config.json (or --no-ask on the hook):

{
  "settings": {
    "reviewChannel": "ask", // "ask" = inline agent prompt (default) | "approver" = node9's own approver
  },
}

• Team setups: when a cloud/team approver is configured (approvers.cloud: true), reviews route to that approver instead — node9 won't let an inline self-approval bypass routed/second-party approval.

Sandbox — run an agent in a jail

When watching isn't enough, node9 sandbox runs the agent inside a disposable container with a kernel-enforced egress allowlist and scoped mounts — while node9's hooks govern and audit every tool call inside the box. The hard version of protection: the agent can only touch the folder you mount and reach the hosts you allow; everything else is dropped at the kernel.

cd ~/my-project
node9 sandbox new        # write node9.sandbox.yaml — what to mount + which hosts to allow
node9 sandbox run        # build + boot the jailed agent (your project at /workspace)
node9 sandbox tail       # watch the agent's actions live, from the host

• Disposable — the container is destroyed on exit; your project edits land on your real disk, nothing else survives.
• Same policy — your existing shields / egress rules / approvals apply inside the box, streamed to the same audit log and dashboard.
• Closes the posture loop — running it flips the Isolation / Egress findings green.

Honest scope (Phase 1): single container, Claude first (Codex next); the agent still holds its own credentials in the box (the egress wall confines them to the allowed hosts) — "the agent never holds a secret" is the credential-broker phase on the roadmap. Requires Docker.

MCP gateway

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.

🔐 MCP tool pinning — rug-pull defense

MCP servers can change their tool definitions between sessions. A compromised or malicious server could silently add, remove, or modify tools after you first trusted it — a rug pull attack.

Node9 pins tool definitions on first use:

• First connection — gateway records a SHA-256 hash of every tool's name, description, and schema
• Subsequent connections — hash is compared; if tools changed, the session is quarantined and every tool call is blocked until a human reviews and approves the change
• Corrupt pin state — fails closed (blocks), never silently re-trusts

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

Other commands

Beyond the three flow commands above (scan / monitor / report):

Command	What it shows	When to use
node9 blast	What an AI agent can reach right now — files, creds, env	First thing to run on any machine
node9 tail	Live stream of every tool call (text-only, no TUI)	Piping into other tools, CI, logs
node9 sessions	Session history with prompt, tool trace, and cost	Reviewing a handoff or past work
node9 dlp	Credential-leak findings in Claude response text	Any time a DLP desktop alert fires
node9 mask	Redact plaintext secrets from local session history files	After a DLP finding — cleans local disk

Plus a live HUD in your Claude Code statusline:

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

Reading the data — what the numbers mean

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

Signal	Likely meaning
Would have blocked ≥ 5 in a week	Agent is attempting high-impact ops; shields are worth reviewing
Single review-git-push rule >50% of findings	Your own rule is firing as intended — not a risk, just supervision
DLP finding in user-prompt tool	You pasted a secret into your own prompt — rotate the key
Agent Loop ×50+ on same file	Agent stuck in edit/test/fix cycle — check context or slow down
MCP tool pin mismatch	Server changed its tools — review before re-trusting
Large MCP response warning	That server is inflating your context window for every subsequent turn
Response DLP alert	Claude wrote a secret in its response text — not blocked, rotate immediately
DLP finding in tool-result	Claude read a file containing a secret (.env, credentials) — rotate the key and run node9 mask
DLP finding in [Shell]	Plaintext secret in ~/.zshrc or ~/.bashrc — every AI session can see it

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/, ~/.gemini/antigravity-*/brain/, ~/.copilot/session-state/, ~/.codex/sessions/ — no API calls, fully offline
• Runtime intercepts tool calls via pre-execution hooks (Claude Code, Codex, Antigravity, GitHub Copilot CLI, Gemini CLI, Opencode, Pi) or via the MCP gateway (Cursor, Windsurf, VSCode, Claude Desktop). All decisions land in ~/.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
• Sandbox generates a Dockerfile + entrypoint that seal an ipset/iptables deny-by-default egress wall, then drop to a non-root agent with node9's daemon + hooks running inside; only the agent's credential file is mounted, never your whole ~/.claude

Full docs

Config reference, smart rules, stateful rules, trusted hosts, approval modes, CLI reference — at node9.ai/docs.

Related projects

• node9-python — Python SDK
• node9-pr-agent — GitHub Action that reviews PRs through Node9

Enterprise

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

License

Apache-2.0

_{Built with ☕ and healthy paranoia.}