MCP.Market

GuardianShield MCP server

by sparkvibe-io·io.github.sparkvibe-io/GuardianShield·v1.2.1·3 stars
No reviews yet

AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs

D42/100grade D
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
D42/100

full report

Adoption
New

3 stars18 downloads/wk

Reviews

Write one

Nobody has reviewed GuardianShield yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

GuardianShield tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it

1 high2 medium
  • Code scan47 source files scanned3/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 209 days ago4/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (3)

  • mediumeval / new Function usedexec.eval
    guardianshield-1.2.1/src/guardianshield/patterns/common.py: … 0.7, ["CWE-79"], ), # eval() with non-literal argument ( …
  • highShell command built from a string (injection risk)exec.shell-concat
    guardianshield-1.2.1/src/guardianshield/patterns/javascript.py: …ion.", "before": "child_process.exec('ls ' + userDir)", "after": "child_proc…
  • mediumsubprocess with shell=Trueexec.shell-true
    guardianshield-1.2.1/src/guardianshield/patterns/python.py: …mand injection risk via subprocess with shell=True.", 0.8, ["CWE-78"], …
Overall 42/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How GuardianShield compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
42/100
higher than 8% of 4,460 AI and agents servers
GitHub stars
3
more than 75% of 2,711 AI and agents servers
Downloads a week
18
more than 5% of 1,538 AI and agents servers with a package

Install GuardianShield in Claude Code, Cursor or VS Code

claude mcp add GuardianShield -- uvx guardianshield
Add to Cursor

GuardianShield: common questions

Is GuardianShield MCP server safe?
Not recommended: it is graded D (42/100). Read the GuardianShield safety report
How do I install GuardianShield?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does GuardianShield need an API key?
No secret keys are declared. It reads 3 settings from the environment.
Is GuardianShield maintained?
The last commit was 246 days ago (2026-03-03). The latest release is v1.2.1.
What can I use instead of GuardianShield?
Servers from other publishers that do the same job: Shellward MCP server, Agent Security Scanner MCP server and agent-device MCP server.
How does GuardianShield compare with other AI and agents MCP servers?
safety score 42/100 (higher than 8% of 4,460 AI and agents servers); github stars 3 (more than 75% of 2,711 AI and agents servers); downloads a week 18 (more than 5% of 1,538 AI and agents servers with a package). Full comparison.

Alternatives to GuardianShield

Same job from other publishers: the closest match first, then the best rated.

  • Shellward
    AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
    A
  • Agent Security Scanner
    Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
    C
  • agent-device
    Open source device layer for AI agents: control mobile, web, TV, and desktop apps over MCP
    A
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • Agent-Native Analytics
    Agent-Native Amplitude/Mixpanel - connect data sources, prompt for charts
    A