Skills/PyPI/unifi-network-mcp

unifi-network-mcp@0.48.1

VERIFIED· install only

Publisher claims: "Unifi Network MCP Server" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher pypi · publishing for 729 daysInstalls 57,110Last detonated 20 min ago
$claude mcp add unifi-network-mcp -- uvx unifi-network-mcp
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 37 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
UNIFI_API_KEYConfiguration, not credentials: UNIFI_MCP_ALLOWED_HOSTS, UNIFI_MCP_COMPOSE_ALLOWED_HOSTS_OVERRIDE, UNIFI_MCP_COMPOSE_ALLOWED_HOSTS_OVERRIDE_SET, UNIFI_MCP_ENABLE_DNS_REBINDING_PROTECTION, UNIFI_MCP_INTERNAL_ALLOWED_HOSTS, UNIFI_MCP_LOG_LEVEL
Where it talks to
no vendor host named in the code
What we saw when it ran
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard. It asks for UNIFI_API_KEY and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --net declared -- uvx unifi-network-mcp

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

What changed since 0.44.0

vet-skills diff unifi-network-mcp 0.44.0 0.48.1

In the sandbox, this version reached for nothing 0.44.0 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 89/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessexited 1: ModuleNotFoundError: No module named 'unifi_core'
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2sprocessexited 1: ModuleNotFoundError: No module named 'unifi_mcp_shared'
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2sprocessexited 1: ModuleNotFoundError: No module named 'unifi_core'
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessexited 1: ModuleNotFoundError: No module named 'unifi_core'
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessexited 1: ModuleNotFoundError: No module named 'unifi_core'
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessexited 1: ModuleNotFoundError: No module named 'mcp'
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessexited 1: ModuleNotFoundError: No module named 'unifi_core'
0.4sprocess8 of 37 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.4sprocessscript backend runs setup only
0.4sprocessscript backend runs setup only
0.5sprocessno install scripts to re-run

Static findings

MEDIUM
Process kill commandsrc/unifi_network_mcp/tools/traffic_routes.py:248 · Process kill command — agent can terminate processesdescription="Enable (true) or disable (false) the kill switch, which blocks traffic if the VPN goes down"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/unifi_network_mcp/tools/traffic_routes.py:216 · Process kill command — agent can terminate processes- kill_switch_enabled: Enable/disable the kill switch (blocks traffic if VPN is down)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/unifi_network_mcp/bootstrap.py:27 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Use only the launcher-supplied environment. Project .env files are never loaded:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈45 tok
1 file · 43 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.