Is @mcp-use/inspector safe to install?

@mcp-use/inspector was flagged as CRITICAL RISK (risk score 4545.5) with 309 findings detected across 528 files. Review the findings before installing.

What security issues were found in @mcp-use/inspector?

Sigil detected 309 findings in @mcp-use/inspector, including patterns related to install_hooks, code_patterns, network_exfil, obfuscation. See the full scan report for details.

@mcp-use/inspector Security Scan — CRITICAL RISK | Sigil

CRITICAL RISK(4545.5)

v0.25.0

23 March 2026, 14:08 UTC

by Sigil Bot

Risk Score

4545.5

Findings

309

Files Scanned

528

Provenance

Registry

https://www.npmjs.com/package/@mcp-use/inspector/v/0.25.0

Scanned From

https://registry.npmjs.org/@mcp-use/inspector/-/inspector-0.25.0.tgz

Findings by Phase

•

Phase Ordering

Phases are ordered by criticality, with the most dangerous at the top. Click any phase header to expand or collapse its findings. Critical phases are expanded by default.

install-pip-setup-exec

CRITICAL

setup.py executes code at install time

package/dist/cdn/inspector.js:110385

	};
	return EI.setup(r, !0), () => DI(r);
}

Why was this flagged?

This setup.py calls subprocess, os.system, exec, or eval during package installation. Legitimate packages rarely need to execute arbitrary commands at install time. This pattern is commonly used by malicious packages to download and run payloads, exfiltrate environment variables, or establish persistence. Rated CRITICAL because it runs with the installer's full permissions.

install-pip-setup-exec

CRITICAL

setup.py executes code at install time

package/dist/cdn/inspector.js:135199

			let r = n && Pmt().getSpan(n);
			if (r) try {
				return this.finishSpanSetup(r, t, e);

Why was this flagged?

This setup.py calls subprocess, os.system, exec, or eval during package installation. Legitimate packages rarely need to execute arbitrary commands at install time. This pattern is commonly used by malicious packages to download and run payloads, exfiltrate environment variables, or establish persistence. Rated CRITICAL because it runs with the installer's full permissions.

install-pip-setup-exec

CRITICAL

setup.py executes code at install time

package/dist/web/assets/index-BEyic8Ea.js:67

|(?![\\s\\S])))+`,`m`),alias:i,inside:{line:{pattern:/(.)(?=[\s\S]).*(?:\r\n?|\n)?/,lookbehind:!0},prefix:{pattern:/[\s\S]/,alias:/\w+/.exec(n)[0]}}}}),Object.defineProperty(e.languages.diff,`PREFIXES`,{value:t})})(e)}qx.displayName=`markup-templating`,qx.aliases=[];function qx(e){e.register(Eb),(function(e){function t(e,t){return`___`+e.toUpperCase()+t+`___`}Object.defineProperties(e.languages[`markup-templating`]={},{buildPlaceholders:{value:function(n,r,i,a){if(n.language===r){var o=n.tokenSt

Why was this flagged?

This setup.py calls subprocess, os.system, exec, or eval during package installation. Legitimate packages rarely need to execute arbitrary commands at install time. This pattern is commonly used by malicious packages to download and run payloads, exfiltrate environment variables, or establish persistence. Rated CRITICAL because it runs with the installer's full permissions.

install-pip-setup-exec

CRITICAL

setup.py executes code at install time

package/dist/web/assets/index-BEyic8Ea.js:1773


Please upgrade your packages to versions that set`,"message tool calls. e.g., `pnpm install @langchain/anthropic`,","pnpm install @langchain/openai`, etc."].join(` `));try{if(n!=null&&r===void 0){let[e,r]=c6(n);t.tool_calls=e??[],t.invalid_tool_calls=r??[]}else t.tool_calls=t.tool_calls??[],t.invalid_tool_calls=t.invalid_tool_calls??[]}catch{t.tool_calls=[],t.invalid_tool_calls=[]}if(t.response_metadata!==void 0&&`output_version`in t.response_metadata&&t.response_metadata.output_version===`v1`&

Why was this flagged?

This setup.py calls subprocess, os.system, exec, or eval during package installation. Legitimate packages rarely need to execute arbitrary commands at install time. This pattern is commonly used by malicious packages to download and run payloads, exfiltrate environment variables, or establish persistence. Rated CRITICAL because it runs with the installer's full permissions.

install-makefile-curl

HIGH

Makefile/script pipes remote content to shell

package/dist/web/assets/powershell-DDAkbMgT.js:1

import{t as e}from"./chunk-zsgVPwQN.js";var t=e(((e,t)=>{function n(e){let t=[`string`,`char`,`byte`,`int`,`long`,`bool`,`decimal`,`single`,`double`,`DateTime`,`xml`,`array`,`hashtable`,`void`],n={$pattern:/-?[A-z\.\-]+\b/,keyword:`if else foreach return do while until elseif begin for trap data dynamicparam end break throw param continue finally in switch exit filter try process catch hidden static parameter`,built_in:`ac asnp cat cd CFS chdir clc clear clhy cli clp cls clv cnsn compare copy cp

Why was this flagged?

A script or Makefile pipes content from a remote URL directly into a shell (curl | sh or wget | bash). This is inherently dangerous because the remote content can change at any time, and the command runs with the current user's permissions. Rated HIGH because it requires manual execution (unlike install hooks) but still executes arbitrary remote code.

Badge

Markdown

[![Sigil Scan](https://sigilsec.ai/badge/npm/@mcp-use/inspector)](https://sigilsec.ai/scans/CB67B32F-B6F4-4A0B-AE42-6DF75C5E1B9C)

HTML

<a href="https://sigilsec.ai/scans/CB67B32F-B6F4-4A0B-AE42-6DF75C5E1B9C"><img src="https://sigilsec.ai/badge/npm/@mcp-use/inspector" alt="Sigil Scan"></a>