Skills/PyPI/mcp-vuln-scanner

mcp-vuln-scanner@1.2.0

VERIFIED· install only

Publisher claims: "AI-powered security vulnerability scanner for MCP (Model Context Protocol) servers with automatic fixes, secret detection, and multi-channel alerts" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher datadruide · publishing for 231 daysInstalls 23Last detonated 4d ago
$claude mcp add mcp-vuln-scanner -- uvx mcp-vuln-scanner
WatchReport an issue

Coverage

Install scripts ran; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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
AI_API_KEYDISCORD_WEBHOOK_URLJIRA_TOKENSLACK_WEBHOOK_URLSMTP_PASSWORDConfiguration, not credentials: AI_MODEL, AI_PROVIDER, JIRA_EMAIL, JIRA_ISSUE_TYPE, JIRA_PROJECT, JIRA_SERVER, MCP_SCANNER_API_URL, MCP_SCANNER_KEY, MCP_SCANNER_LICENSE, SMTP_PORT, SMTP_SERVER, SMTP_USER
Where it talks to
no vendor host named in the codeAlso nist.gov, onrender.com, jsdelivr.net, githubusercontent.com, mitre.org — not the publisher's domain; check what for before connecting.
What the honeypot saw
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 nist.gov, onrender.com, jsdelivr.net, githubusercontent.com, mitre.org as well as its own vendor. The guard injects AI_API_KEY, DISCORD_WEBHOOK_URL, JIRA_TOKEN, SLACK_WEBHOOK_URL, SMTP_PASSWORD only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx mcp-vuln-scanner

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; install scripts ran; no agent task scenario for this bundle) on 2026-11-10 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 · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessexited 1: ModuleNotFoundError: No module named 'setuptools'
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.1sprocesssecond launch, clock +45 days, CI unset
0.1sprocessexited 1: ModuleNotFoundError: No module named 'setuptools'

Static findings

MEDIUM
Python subprocess execution detectedsrc/scanner/analyzers/supply_chain.py:80 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_dangerous_ops.py:36 · Python subprocess execution detectedresult = subprocess.run(cmd, shell=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)src/scanner/discovery/remote.py:14 · MCP server using network transport (SSE/HTTP) — data sent over network"""Erkennt und scannt remote MCP-Server über HTTP/SSE"""Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04

Cost to the agent

Instructions loaded
≈75 tok
1 file · 34 in bundle

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

Known vulnerabilities

No advisories in OSV for mcp-vuln-scanner@1.2.0 as of 4d ago. This is the package itself, not its dependencies.