Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

MCP stdio ShellGuard

NPM · MCP-STDIO-SHELLGUARD · SCANNED SEP 21

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

0 this week 76 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 42 of 131 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability56
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 518 tokens (~64/item across 8 items; 8 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the MCP stdio ShellGuard server?

MCP stdio ShellGuard runs locally as an npm package, launched with npx -y mcp-stdio-shellguard. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · mcp-stdio-shellguard

# add to Claude Code
claude mcp add io-studiomeyer-stdio-shellguard -- npx -y mcp-stdio-shellguard
// .cursor/mcp.json
{
  "mcpServers": {
    "io-studiomeyer-stdio-shellguard": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-stdio-shellguard"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "io-studiomeyer-stdio-shellguard": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-stdio-shellguard"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add io-studiomeyer-stdio-shellguard -- npx -y mcp-stdio-shellguard
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-studiomeyer-stdio-shellguard": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mcp-stdio-shellguard"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add io-studiomeyer-stdio-shellguard --command npx --arg -y --arg mcp-stdio-shellguard
# ~/.hermes/config.yaml
mcp_servers:
  io-studiomeyer-stdio-shellguard:
    command: "npx"
    args: ["-y", "mcp-stdio-shellguard"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "io-studiomeyer-stdio-shellguard": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "mcp-stdio-shellguard"
      ]
    }
  }
}
# add to Vellum
assistant mcp add io-studiomeyer-stdio-shellguard -t stdio -c npx -a -y mcp-stdio-shellguard
// mcp.json
{
  "mcpServers": {
    "io-studiomeyer-stdio-shellguard": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-stdio-shellguard"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 20 Sept 26 0
    • Security disclosure: unverified → fail functional
  • 19 Sept 26 −3
    • Security disclosure: fail → unverified functional
    • Stability: pass → 0.80 functional
  • 17 Sept 26 +1
    • Stability: 0.97 → pass security
  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 +1
    • Security disclosure: unverified → fail functional
    • Package version: 0.1.1 → 0.1.2 functional
  • 12 Sept 26 0
    • Security disclosure: fail → unverified functional
  • 11 Sept 26 −3
    • Stability: pass → 0.80 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Sept 2026 · Analysed npm/mcp-stdio-shellguard@0.1.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 131 packages
Packages resolved 131
Stale 42
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 8 exposed · ~518 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
audit_report ~38

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

NameTypeReqDescription
findings
formatstringyes

No output schema declared.

No examples provided.

audit_source ~69

Scan a TypeScript / JavaScript path for unsanitised child_process.exec / spawn / execFile calls and other shell-injection anti-patterns. Returns AuditFinding[] + summary.

NameTypeReqDescription
ignoreGlobsarray
pathstringyes
severityFloorstring

No output schema declared.

No examples provided.

guard_exec ~93

Defended replacement for child_process.exec. Forces an args[] vector, runs through allowlist + sandbox + replay window. Returns stdout/stderr/exitCode.

NameTypeReqDescription
argsarrayyes
blockOnReplayboolean
commandstringyes
cwdstring
envobject
timeoutMsnumber
toolNamestringyes

No output schema declared.

No examples provided.

guard_spawn ~85

Defended replacement for child_process.spawn. Returns stdout/stderr SHA-256 hashes instead of full bodies. Rejects shell:true.

NameTypeReqDescription
argsarrayyes
cwdstring
envobject
fdBudgetnumber
filestringyes
shellboolean
toolNamestringyes

No output schema declared.

No examples provided.

register_allowlist ~78

Register a tool name with its allowed executable + args regex patterns. Without registration the default-deny applies and guard_exec/guard_spawn refuse to run.

NameTypeReqDescription
argsPatternsarrayyes
cwdPatternstring
executablestringyes
sandboxProfilestring
toolNamestringyes

No output schema declared.

No examples provided.

replay_check ~68

Compute the canonical SHA-256 hash for an invocation and report whether the same hash is already in the LRU sliding window.

NameTypeReqDescription
argsarrayyes
cwdstring
envobject
executablestringyes
recordboolean

No output schema declared.

No examples provided.

sandbox_status ~45

Report the active sandbox profile + concrete limits (timeout, byte caps, fd budget, cgroup-v2 active flag) for a registered tool.

NameTypeReqDescription
toolNamestring

No output schema declared.

No examples provided.

trust_tier ~42

Derive the LOW / MEDIUM / HIGH / CRITICAL trust tier for a registered tool plus improvement hints to lift it.

NameTypeReqDescription
toolNamestringyes

No output schema declared.

No examples provided.

Common questions

What is the MCP stdio ShellGuard server?

MCP stdio ShellGuard is listed in the public MCP registry as io.studiomeyer/stdio-shellguard. Defense-in-depth for MCP stdio servers: shell-injection guard, AST audit CLI, RCE blocking. This page covers its npm package (mcp-stdio-shellguard).

Is the MCP stdio ShellGuard server safe to use?

MCP stdio ShellGuard scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the MCP stdio ShellGuard server expose?

MCP stdio ShellGuard exposes 8 tools: guard_exec, guard_spawn, register_allowlist, audit_source, audit_report, and 3 more. Their descriptions and schemas cost roughly 518 tokens of context every time the server is loaded.

Is the MCP stdio ShellGuard server still maintained?

MCP stdio ShellGuard is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the MCP stdio ShellGuard server under?

MCP stdio ShellGuard declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.