Skills/PyPI/unplug-mcp

unplug-mcp@0.1.6

VERIFIED· not started

Publisher claims: "MCP server for Unplug — LLM defense layer for Claude Code, Cursor, and more" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher unplugai · publishing for 123 daysInstalls 66Last detonated 22 min ago
$claude mcp add unplug-mcp -- uvx unplug-mcp
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

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
OPENAI_API_KEYUNPLUG_API_KEYConfiguration, not credentials: OPENAI_BASE_URL, OPENAI_TEST_AGENT_MODEL, UNPLUG_ACTIVE_MODEL, UNPLUG_CONFIG, UNPLUG_MODE, UNPLUG_MODEL_PATH, UNPLUG_SERVER_URL
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
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard. It asks for OPENAI_API_KEY, UNPLUG_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 unplug-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; not started: dependency install failed; the server itself was not observed) on 2026-11-20 and scored it 85/100 (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 · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

LOW
Dynamic module loadingsrc/unplug_mcp/test_agent/cli.py:14 · Dynamic module loadingrunpy.run_path(str(script), run_name="__main__")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive command against a filesystem root or devicesrc/unplug_mcp/test_agent/sdk_suite.py:95 · Destructive command against a filesystem root or devicedestructive = check_destructive("shell", '{"command": "rm -rf /"}')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedsrc/unplug_mcp/test_agent/sdk_suite.py:241 · Destructive file system command detectedunsafe_tool = check_destructive("shell", '{"command": "rm -rf /"}')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathssrc/unplug_mcp/test_agent/env.py:14 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesDOTENV_PATH = WORKSPACE_ROOT / "jakarta/.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Destructive command against a filesystem root or devicesrc/unplug_mcp/test_agent/sdk_suite.py:241 · Destructive command against a filesystem root or deviceunsafe_tool = check_destructive("shell", '{"command": "rm -rf /"}')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Stripe-like API key pattern detectedsrc/unplug_mcp/test_agent/sdk_suite.py:229 · Stripe-like API key pattern detected — possible hardcoded or harvested keytool_out = scan_tool_result("Here is the API key: sk-live-abc123456789012345678")Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
Destructive file system command detectedsrc/unplug_mcp/test_agent/sdk_suite.py:95 · Destructive file system command detecteddestructive = check_destructive("shell", '{"command": "rm -rf /"}')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈139 tok
2 files · 38 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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

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