Atlas / MCP servers / node9-ai / Node9 Proxy

Node9 ProxyBLOCK

mcp/node9-ai/node9-proxy

Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.

Verdict
BLOCK
Grade
F
Trust score
42 /100
Exposed tools
32 23r · 8w · 1d
Transport
stdio
License
Apache-2.0
Stars
220
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

🛡️ node9 Access control for AI agents Your AI agents can reach Slack, GitHub, email, and your database.node9 decides what they may do with each one.

<img src="https://img.shields.io/badge/node9-self--scanned-a855f7?style=flat&labelColor=%231A1A2E&logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAxNCAxNCI+PHBhdGggZmlsbD0iI0Y1RTlGRiIgZmlsbC1ydWxlPSJldmVub2RkIiBjbGlwLXJ1bGU9ImV2ZW5vZGQiIGQ9Ik03IDAuNCAxLjYgMi41djQuMmMwIDMuMSAyLjMgNS42IDUuNCA2LjkgMy4xLTEuMyA1LjQtMy44IDUuNC02LjlWMi41TDcgMC40Wm0wIDEuNSAzLjkgMS41djMuM2MwIDIuMy0xLjYgNC4yLTMuOSA1LjMtMi4zLTEuMS0zLjktMy0zLjktNS4zVjMuNEw3IDEuOVptMCAyLjJhMS45IDEuOSAwIDAgMC0xIDMuNXYxLjZoMlY3LjZhMS45IDEuOSAwIDAgMC0xLTMuNVoiLz48L3N2Zz4K" alt="node9 self-scanned" />

Read from source at commit f26ea204c6afOBSERVED · 2026-10-11
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code (npm)
claude mcp add node9-ai -- npx -y [email protected] mcp-server
03

Exposed tools (32)

23 read · 8 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

ToolRiskDescription
big_queryreadReturns lots of data
deletedestructiveDelete all
echoreadReturns a fixed line
listreadList items
my-gmailreadProtect Gmail MCP creds + gate sends
my-shieldreadA test shield
node9_approver_listreadList all node9 approver channels and their current enabled/disabled state.
node9_approver_setwriteEnable or disable a specific node9 approver channel in the global config (~/.node9/config.json).
node9_audit_getreadRead recent entries from the node9 audit log (~/.node9/audit.log). Each entry shows
node9_config_getreadRead the current node9 configuration: security mode, approver channels, timeouts,
node9_egress_denywriteAdd a host to the egress deny list (deny always wins over allow). Only adds
node9_egress_protectreadTurn on egress control (or strengthen it). mode=
node9_egress_statusreadShow egress (outbound network) control: whether it is enabled, the mode
node9_explainreadPreview exactly how node9 would evaluate a tool call BEFORE running it — the full
node9_policy_getreadShow all active smart rules in detail — name, tool, verdict, conditions, and reason.
node9_posturewriteRun the node9 security posture scorecard for the agent on this host — grades how exposed
node9_reportreadShow an activity and security report: tool call counts, blocks, DLP findings, agent cost,
node9_rule_addwriteAdd a new protective smart rule to the global node9 config (~/.node9/config.json).
node9_scanreadScan all AI agent history (Claude + Gemini) and report what node9 would have blocked or
node9_sessionreadList recent AI agent sessions with per-session summaries: tool calls, cost, modified files,
node9_shield_disablewriteDisable a node9 shield. WEAKENING action — refused over MCP by default (a human must run
node9_shield_enablewriteEnable a node9 shield for a specific service. Shields only add protection — they cannot
node9_shield_listreadList all available node9 shields and which ones are currently active.
node9_statusreadShow the current node9 protection status: mode, daemon state, pause state,
read_filereadRead a file
read_pagereadRead
redisreadall-allow shadow
send_emailwriteSend email to recipient
tool_v1readVersion 1
tool_v2readVersion 2
user-jailreaduser jail
write_filewriteWrite a file
04

Trust audit

BLOCKgrade F · trust 42/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryFAIL
L1Static analysis of the codeFAIL
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (4 observation(s))
Network
declared (16 observation(s))
Shell
declared (4 observation(s))
Dependencies
not all pinned
Secrets in source
found

Findings (25)

HIGHInventory / provenance · inv.suspicious_name · CWE-1104
src/utils/hook-payload.ts
hook-payload.ts
Why it matters. member named after an attack tool
Fix. remove or justify
HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
resolve-version.js:73
return exec(process.execPath, [cli, ...args], opts);
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
HIGHNetwork egress · net.env_exfil · CWE-200, CWE-319
packages/policy-engine/src/policy/pipe-chain.ts:67
id_rsa ... curl
Why it matters. reads secrets in the same file that sends data out
HIGHNetwork egress · net.env_exfil · CWE-200, CWE-319
packages/policy-engine/src/scan/canonical.ts:258
~/.ssh ... curl
Why it matters. reads secrets in the same file that sends data out
HIGHNetwork egress · net.metadata_ip · CWE-200, CWE-319
packages/policy-engine/src/catalog-text.ts:192
example: 'curl http://169.254.169.254/latest/meta-data/iam/',
Why it matters. cloud metadata endpoint: the classic SSRF credential grab
HIGHNetwork egress · net.metadata_ip · CWE-200, CWE-319
packages/policy-engine/src/catalog.ts:352
catches: '169.254.169.254 and its peers, link-local and multicast',
Why it matters. cloud metadata endpoint: the classic SSRF credential grab
HIGHObfuscation / stealth · obf.rtl_override · CWE-506, CWE-94
packages/policy-engine/src/dlp/normalize.ts:12
const INVISIBLE_RE = /[͏----︀-️]|[\u{E0000}-\u{E007F}]/gu;
MEDIUMNetwork egress · net.beacon_words · CWE-200, CWE-319
comment.js:63
if (/exfil/.test(rule)) return "Where does the data go: your own service, or someone else's?";
MEDIUMNetwork egress · net.beacon_words · CWE-200, CWE-319
comment.js:301
const exfil = companions.some((c) => c.check === 'CI-4') || /exfiltrat|read env/.test(sig);
MEDIUMNetwork egress · net.beacon_words · CWE-200, CWE-319
comment.js:311
return rce && exfil
MEDIUMNetwork egress · net.beacon_words · CWE-200, CWE-319
comment.js:1032
signals: ['agent has arbitrary shell (bare Bash) → can read env and exfiltrate'],
MEDIUMNetwork egress · net.beacon_words · CWE-200, CWE-319
comment.js:1037
'crit RCE+exfil → run-code-and-steal'
MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
packages/policy-engine/src/catalog-text.ts:185
example: 'curl http://192.168.1.10/admin',
MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
packages/policy-engine/src/catalog-text.ts:192
example: 'curl http://169.254.169.254/latest/meta-data/iam/',
MEDIUMObfuscation / stealth · obf.zero_width · CWE-506, CWE-94
packages/policy-engine/src/dlp/normalize.ts:12
const INVISIBLE_RE = /[͏----︀-️]|[\u{E0000}-\u{E007F}]/gu;
MEDIUMHard-coded secrets · secret.db_uri · CWE-798, CWE-321
src/__tests__/dlp.test.ts:188
expect(scanArgs({ env: 'redis://u:abc@host' })).toBeNull();
MEDIUMHard-coded secrets · secret.db_uri · CWE-798, CWE-321
src/__tests__/dlp.test.ts:199
expect(scanArgs({ env: 'mysql://root:<your-password>@host' })).toBeNull();
MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321
src/__tests__/action-upload.test.ts:31
const TOKEN = 'header.payload.signature';
MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321
src/__tests__/api-url-second-reader.integration.test.ts:29
JSON.stringify({ default: { apiKey: 'nk_probe_not_a_real_key', apiUrl } })
MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321
src/__tests__/dlp.test.ts:601
const token = 'pk.eyJ1IjoibXl1c2VyIiwiYSI6ImFiY2QifQ.AbCdEfGhIjKlMnOpQrSt';
MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321
src/__tests__/redactor.test.ts:13
expect(redactSecrets('api_key="ABCDEFGHIJ1234567890"')).toContain('api_key="********');
MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59
delete
Why it matters. 1 tool(s) can delete or overwrite
Fix. prefer a read-only mode or scoped tokens; the page states the blast radius
LOWInventory / provenance · inv.hidden_file · CWE-1104
.prettierignore
.prettierignore
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
.releaserc.json
.releaserc.json
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.suspicious_name · CWE-1104
src/__tests__/fixtures/ci-check/item-reach/base-action-prompt-file-from-payload.yml
base-action-prompt-file-from-payload.yml
Why it matters. member named after an attack tool
Fix. remove or justify

Gates applied: no_behavioural_pass.

Audited 2026-10-11 · audit v0.4.1 · source sha f26ea204c6affull audit observations/trust-audit/mcp-server/node9-ai__node9-proxy.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-11f26ea204c6afBLOCKF42first audit
06

Questions

What is the @node9/proxy MCP server?

Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.

What tools does @node9/proxy expose?

32 in total: 23 read-only, 8 that write, and 1 that can delete or overwrite (delete). Every one is listed on this page with its risk.

Is @node9/proxy safe to connect to an agent?

No — not without reading the findings first. The audit graded it F (42/100) and found 7 critical or high issues in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does @node9/proxy need?

It reads ANTHROPIC_API_KEY, GEMINI_API_KEY, GH_TOKEN, GITHUB_TOKEN and NODE9_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does @node9/proxy run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as @node9/policy-engine at 2.30.1.

How current is this page?

The grade is for one exact copy of the source (f26ea204c6af), read on 2026-10-11. The repository is watched and re-audited when it changes.

Advertisement