Skills/Glama/unifi-mcp

unifi-mcp@0.4.0

VERIFIED· install only

Publisher claims: "Enables an LLM client to diagnose a UniFi network through 39 tools covering devices, clients, WAN and VPN state, events, metrics, traffic reports, threat summaries, and security posture audits. Guarded write tools allow blocking clients, restarting devices, and managing networks, WiFi broadcasts, and hotspot vouchers, with previews and confirmation required for changes that could cut off protected networks or the gateway." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher jfms7s · publishing for 8 daysInstalls 0Last detonated 8d ago
$npx skills add unifi-mcp
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
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_KEYUNIFI_MCP_TOKENUNIFI_SITE_MANAGER_API_KEYConfiguration, not credentials: FIREWALL_PATHS, UNIFI_MCP_ACCEPTED_FINDINGS, UNIFI_MCP_PORT, UNIFI_MCP_PROTECTED_NETWORKS, UNIFI_MCP_TRANSPORT, UNIFI_TLS_FINGERPRINT, UNIFI_URL
Where it talks to
no vendor host named in the codeAlso ui.com — not the publisher's domain; check what for before connecting.
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, and read the third-party hosts first. The code names ui.com as well as its own vendor. The guard injects UNIFI_API_KEY, UNIFI_MCP_TOKEN, UNIFI_SITE_MANAGER_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- <the server's command>

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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 and scored it 81/100 (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 · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

LOW
URL to a private-network addressscripts/capture-fixtures.ts:6 · URL to a private-network address — a LAN or development target* UNIFI_URL=https://192.168.10.1 npx tsx scripts/capture-fixtures.tsFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
LOW
URL to a private-network addresstest/config.test.ts:6 · URL to a private-network address — a LAN or development targetUNIFI_URL: 'https://192.168.0.1',Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Access to sensitive file pathsscripts/capture-fixtures.ts:5 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files* set -a; . ~/.config/unifi-mcp/.env; set +aFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
URL to a private-network addressscripts/spike-writes.ts:6 · URL to a private-network address — a LAN or development target* UNIFI_URL=https://192.168.10.1 npx tsx scripts/spike-writes.tsFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
LOW
URL to a private-network addresstest/config.test.ts:14 · URL to a private-network address — a LAN or development targetconsole: { baseUrl: 'https://192.168.0.1', apiKey: 'api-key', tls: { fingerprint: FP } },Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Access to sensitive file pathsscripts/spike-writes.ts:5 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files* set -a; . ~/.config/unifi-mcp/.env; set +aFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
URL with embedded credentialstest/config.test.ts:68 · URL with embedded credentials — may be phishing or credential leakingexpect(() => loadConfig({ ...base, UNIFI_URL: 'https://admin:[email protected]' })).toThrow(Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
LOW
URL to a private-network addresstest/config.test.ts:54 · URL to a private-network address — a LAN or development targetUNIFI_URL: 'http://192.168.0.1',Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with embedded credentialstest/config.test.ts:44 · URL with embedded credentials — may be phishing or credential leakingexpect(() => loadConfig({ ...base, UNIFI_URL: 'https://admin:hunter2@[bad' })).toThrow(Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
URL with embedded credentialstest/http/errors.test.ts:39 · URL with embedded credentials — may be phishing or credential leakingbaseUrl: 'https://user:[email protected]',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
LOW
URL to a private-network addresstest/http/errors.test.ts:29 · URL to a private-network address — a LAN or development target'Cannot reach UniFi at https://192.168.10.1 for GET /v1/sites: connect ECONNREFUSED 192.168.10.1:443',Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
LOW
URL to a private-network addresstest/config.test.ts:58 · URL to a private-network address — a LAN or development targetexpect(loadConfig(insecure).console.baseUrl).toBe('http://192.168.0.1');Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
LOW
URL to a private-network addresstest/config.test.ts:62 · URL to a private-network address — a LAN or development targetexpect(() => loadConfig({ ...base, UNIFI_URL: 'http://192.168.0.1' })).toThrow(Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
LOW
URL to a private-network addresstest/http/errors.test.ts:26 · URL to a private-network address — a LAN or development targetbaseUrl: 'https://192.168.10.1',Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

Cost to the agent

Instructions loaded
≈32 tok
1 file · 81 in bundle

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

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.