MCP.Market

MCP stdio ShellGuard MCP server

by studiomeyer.io·io.studiomeyer/stdio-shellguard·v0.1.3
No reviews yet

Defense-in-depth for MCP stdio servers: shell-injection guard, AST audit CLI, RCE blocking.

C60/100grade C
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
C60/100

full report

Adoption
Growing

0 stars263 downloads/wk

Reviews

Write one

Nobody has reviewed MCP stdio ShellGuard yet.

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

MCP stdio ShellGuard tools (8)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • audit_report

    Format an AuditScanResult as markdown / json / sarif. Pure pass-through transformer.

  • audit_source

    Scan a TypeScript / JavaScript path for unsanitised child_process.exec / spawn /

  • guard_exec

    Defended replacement for child_process.exec. Forces an args[] vector,

  • guard_spawn

    Defended replacement for child_process.spawn. Returns stdout/stderr SHA-256 hashes

  • register_allowlist

    Register a tool name with its allowed executable + args regex patterns.

  • replay_check

    Compute the canonical SHA-256 hash for an invocation and report whether the same

  • sandbox_status

    Report the active sandbox profile + concrete limits (timeout, byte caps, fd budget,

  • trust_tier

    Derive the LOW / MEDIUM / HIGH / CRITICAL trust tier for a registered tool plus

Public scan report

scanner v0.1.10 · 2026-11-02 · same rubric, same numbers if you re-run it

1 high1 medium
  • Code scan36 source files scanned8/25
  • –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 1 days ago15/15
  • Maintainer identitynamespace and repository owner differ4/10

Findings (2)

  • highShell command built from a string (injection risk)exec.shell-concat
    dist/audit/bindings.js: …import cp from "node:child_process"; cp.exec(`ls ${x}`)` * via a default/namespace im…
  • mediumeval / new Function usedexec.eval
    dist/audit/patterns.js: … severity: "CRITICAL", label: "eval(...)", test: ({ callee }) => cal…
Overall 60/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How MCP stdio ShellGuard compares

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

Safety score
60/100
higher than 15% of 48,243 servers
Tools
8
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
263
more than 79% of 12,306 servers with a package

What its tools let an agent do: 7 read · 1 create

Release history: 2 versions in the registry since 2026-08-19, latest 2026-11-01, typically one every 74 days.

Install MCP stdio ShellGuard in Claude Code, Cursor or VS Code

Runs npx -y mcp-stdio-shellguard on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add stdio-shellguard -- npx -y mcp-stdio-shellguard
Add to Cursor

What the publisher says

From the MCP stdio ShellGuard repository's README, as published. We do not edit it. Read it on GitHub

<!-- studiomeyer-mcp-stack-banner:start -->

Part of the StudioMeyer MCP Stack — Built in Mallorca 🌴 · ⭐ if you use it

<!-- studiomeyer-mcp-stack-banner:end -->

mcp-stdio-shellguard

<!-- badges --> <!-- /badges -->Defense-in-depth bundle for MCP stdio servers. Wraps child_process.exec/spawn with allowlist + sandbox + replay-detection, plus an AST audit CLI (mcp-shellguard-audit) that scans MCP server sources for unsanitized shell calls. Closes the Ox-Security MCP stdio-RCE class (200k vulnerable servers, May 2026 disclosure).

  • MCP spec: 2025-06-18
  • SDK: @modelcontextprotocol/sdk ^1.29.0
  • Node: >= 20
  • License: MIT
  • Author: Matthias Meyer (StudioMeyer)

Install

npm install mcp-stdio-shellguard

Or run the audit CLI directly without installing:

npx -y -p mcp-stdio-shellguard mcp-shellguard-audit scan ./src

What it gives you

Three layers, opt-in piecewise:

own MCP server. Default-deny allowlist, sandbox profiles, replay window.

  1. Library API — drop-in guardExec / guardSpawn you call from your

12 anti-patterns from LOW (no timeout) to CRITICAL (exec(\...${userInput}...\)).

  1. Audit CLI — mcp-shellguard-audit scan walks the AST, reports

so the MCP Inspector / Claude Desktop can drive the bundle directly.

  1. Reference MCP server — mcp-stdio-shellguard-demo exposes 8 tools

Tools (reference server)

Sandbox profiles

Caller can tighten via timeoutMs / fdBudget per call. Caller cannot widen beyond the profile.

Trust tiers

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

MCP stdio ShellGuard: common questions

Is MCP stdio ShellGuard MCP server safe?
With care: it is graded C, so read the findings first (60/100). Read the MCP stdio ShellGuard safety report
How do I install MCP stdio ShellGuard?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does MCP stdio ShellGuard need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is MCP stdio ShellGuard maintained?
The last commit was 4 days ago (2026-11-01). The latest release is v0.1.3.
How does MCP stdio ShellGuard compare with other MCP servers?
safety score 60/100 (higher than 15% of 48,243 servers); tools 8 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

More from studiomeyer.io →