Skills/npm/mcp

mcp@0.18.26

CAUTION

Publisher claims: "Official Model Context Protocol (MCP) server for NineDeploy AI integration" Observed in sandbox: sends data to 127.0.0.1.

Registry npm (MCP server)Publisher ninedeploy · publishing for 88 daysInstalls 4,857Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Started with a decoy NINEDEPLOY_TOKEN; tool list observed. Tool calls with a real credential not tested.
Tested
server startup with a tagged decoy in NINEDEPLOY_TOKEN · MCP initialize and tools/list · every tool description, for hidden instructions · where the decoy credential went · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with a real credential
Needs
NINEDEPLOY_TOKEN — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

Before you give it your token

It will ask for
NINEDEPLOY_TOKENConfiguration, not credentials: NINEDEPLOY_MCP_READONLY, NINEDEPLOY_URL
Where it talks to
no vendor host named in the code
What the honeypot saw
no credential files read · contacted 127.0.0.1 (undeclared)
What we could not test
what the tools do when called with a real credential

Find out what these hosts are first. In the honeypot it contacted 127.0.0.1, which nothing in the package names as its own. If that is the vendor's service, fine; if you cannot place it, do not connect it.

$vet-skills run --net 127.0.0.1 -- npx -y @ninedeploy/mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-11 and scored it 71/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: sends data to 127.0.0.1.

Behavior trace

Honeypot run · 52 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
11sprocessdependency install exit 0
31sprocessrelaunched with a decoy NINEDEPLOY_TOKEN (tagged; nothing real)
51snetworkCONNECT tcp://127.0.0.1:3000 · not in the allow-list, refused
51sclaimed64 tools with a decoy NINEDEPLOY_TOKEN: list_services, get_service, service_logs, list_deploys, list_domains, list_databases, list_projects, list_alerts, activity_log, system_stats, topology, health, deploy_service, restart_service, cancel_deploy, remove_deploy, rollback_deploy, list_queue, list_plugins, marketplace_plugins, install_plugin, enable_plugin, disable_plugin, uninstall_plugin, list_configs
51sprocessscript backend runs setup only
51sprocessno install scripts to re-run

Static findings

No findings across 2,227 lines in 16 files.

Cost to the agent

Instructions loaded
≈54 tok
1 file · 16 in bundle
Tool list per prompt
≈5,184 tok
64 tools · 81 per tool
Handshake
1037 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 103

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for @ninedeploy/mcp@0.18.26 as of 3d ago. This is the package itself, not its dependencies.

What would make this Verified

9 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
  2. Unclaimed publisher≈ +8 on the totalClaim ninedeploy: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim ninedeployPropose a patch to the maintainer