Puppeteer (williamzujkowski) MCP Server
puppeteer-mcp
npm
v1.1.2
Published by williamzujkowski — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Beta - AI-enabled browser automation platform seeking production feedback
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 21.7 = 78. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −15.4 | Assembled command execution and dynamic evaluation in the same server MTC-SRC-011 | injection |
| −6.3 | Untrusted input concatenated into a command sink MTC-SRC-009 | injection |
2. Client adoption risk — 78 − 7 = 71. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 8
high Dynamic evaluation of a non-literal value (dist/puppeteer/actions/execution/validation/control-flow-validator.js)MTC-SRC-010
In the server's implementation (`dist/puppeteer/actions/execution/validation/control-flow-validator.js:130`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try { new Function(func); } catch { this.addError(errors, 'function', 'Inv
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/puppeteer/actions/execution/validation/control-flow-validator.js
high Assembled command execution and dynamic evaluation in the same serverMTC-SRC-011
The implementation both builds shell commands out of runtime values (`dist/puppeteer/pool/browser-health.js`) and evaluates runtime values as code (`dist/puppeteer/actions/execution/validation/control-flow-validator.js`). Each is a separate arbitrary-execution primitive; a server exposing both gives anything that reaches either one a direct path to running attacker-chosen code. These two sinks are in different files — confirm whether they are actually connected, or are unrelated code paths (e.g. a vendored bundle plus a CLI wrapper).
Fix: Remove the dynamic eval, and pass command arguments as an argv array instead of building a shell string. If both are genuinely required, constrain and validate every value that can reach them.
Location: server implementation
high Dynamic code execution in server code (dist/puppeteer/actions/execution/validation/control-flow-validator.js)MTC-SRC-001
In the server's implementation (`dist/puppeteer/actions/execution/validation/control-flow-validator.js:130`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try { new Function(func); } catch { this.addError(errors, 'function', 'Inv
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/puppeteer/actions/execution/validation/control-flow-validator.js
high Shell/command execution in server code (dist/grpc/services/command-executor.js)MTC-SRC-002
In the server's implementation (`dist/grpc/services/command-executor.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: import { spawn } from 'child_process'; import { logSecurityEvent, SecurityEventType } from '../../utils/logger.js'; imp
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/grpc/services/command-executor.js
high Shell/command execution in server code (dist/puppeteer/actions/execution/wait/function-strategy.js)MTC-SRC-002
In the server's implementation (`dist/puppeteer/actions/execution/wait/function-strategy.js:13`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ess' }, { pattern: /child_process/gi, name: 'child_process' }, { pattern: /__proto__/gi, name: 'prototype pollut
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/puppeteer/actions/execution/wait/function-strategy.js
high Shell/command execution in server code (dist/puppeteer/pool/browser-health.js)MTC-SRC-002
In the server's implementation (`dist/puppeteer/pool/browser-health.js:9`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: cSync } = await import('child_process'); const stats = execSync(`ps -p ${process.pid} -o %mem,%cpu | tail -1`).t
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/puppeteer/pool/browser-health.js
high Shell/command execution in server code (dist/puppeteer/pool/resource-management/browser-resource-monitor.js)MTC-SRC-002
In the server's implementation (`dist/puppeteer/pool/resource-management/browser-resource-monitor.js:2`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ; import { exec } from 'child_process'; import { createLogger } from '../../../utils/logger.js'; const logger = createLo
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/puppeteer/pool/resource-management/browser-resource-monitor.js
medium Untrusted input concatenated into a command sink (dist/puppeteer/pool/browser-health.js)MTC-SRC-009
In the server's implementation (`dist/puppeteer/pool/browser-health.js:10`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ; const stats = execSync(`ps -p ${process.pid} -o %mem,%cpu | tail -1`).toString(); const [mem, cpu] = s
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/puppeteer/pool/browser-health.js
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v1.1.2 latest |
C 71/100 | 8 | 1.13.0 | 2026-09-07 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan puppeteer-mcp --onlineOther implementations of Puppeteer 9
Independent packages implementing the same tool, scanned with the same engine. Compare all 10 side by side →
Experimental browser automation server using Puppeteer, inspired by the original @modelcontextprotocol/server-puppeteer.
Experimental MCP server for browser automation using Puppeteer (inspired by @modelcontextprotocol/server-puppeteer)
MCP server for controlling Chromium via Puppeteer
Puppeteer tools for browser automation and web scraping.
Simple Puppeteer-based server that provides browser abilities to LLMs.
Puppeteer-based search and page-scraping tools that give AI web access.
More in Browser Automation
Model Context Protocol (MCP) server that integrates AgentQL data extraction capabilities.
Screenshot any URL or HTML as PNG/JPEG/WebP from your AI agent. Full-page, clean, no install.
MCP server for aria51 accessibility scanner
Bridge any browser web app to Claude Code via MCP
Browserbase’s official MCP server: cloud headless browsers for agents, with sessions and screenshots.
MCP server for AI web browser automation using Browserbase and Stagehand