Playwriter Browser MCP Server
playwriter-browser-mcp
npm
v0.1.4
Published by an unidentified publisher — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
MCP server bridging Playwriter's Chrome extension with Playwright-style structured tools for VisionClaw
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 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 8 = 92. 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 |
| −2 | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read |
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 7
high Tool "browser_run_code" exposes command/code executionMTC-CAP-001
Tool "browser_run_code" appears to run shell commands or evaluate code (keyword "run_code" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool browser_run_code
high Dynamic code execution in server code (dist/tools/run-code.js)MTC-SRC-001
In the server's implementation (`dist/tools/run-code.js:11`): 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: const fn = new Function("page", `return (${code})(page);`); const result = await fn(page);
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/run-code.js
high Dynamic code execution in server code (src/tools/run-code.ts)MTC-SRC-001
In the server's implementation (`src/tools/run-code.ts:22`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: eval const fn = new Function("page", `return (${code})(page);`); const result: unknown = await (fn as Fu
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 src/tools/run-code.ts
high Shell/command execution in server code (dist/browser/connection.js)MTC-SRC-002
In the server's implementation (`dist/browser/connection.js:3`): 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: { execFile } from "node:child_process"; import net from "node:net"; import { BrowserState } from "./state.js"; const CON
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/browser/connection.js
high Shell/command execution in server code (src/browser/connection.ts)MTC-SRC-002
In the server's implementation (`src/browser/connection.ts:3`): 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: { execFile } from "node:child_process"; import net from "node:net"; import type { Config } from "../config.js"; import {
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 src/browser/connection.ts
low Mutating tool "browser_run_code" declares no destructiveHintMTC-CAP-005
Tool "browser_run_code" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool browser_run_code
low Shell/command execution in packaging/dev tooling (dist/tools/install.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/tools/install.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: { execFile } from "node:child_process"; import { textResult, errorResult } from "../utils/result.js"; export function re
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/tools/install.js
Tools 38
Each tool and what it can reach — statically extracted from the published source.
browser_run_coderuns code / shellbrowser_clickno sensitive capabilitybrowser_closeno sensitive capabilitybrowser_console_messagesno sensitive capabilitybrowser_dragno sensitive capabilitybrowser_evaluateno sensitive capabilitybrowser_file_uploadno sensitive capabilitybrowser_fill_formno sensitive capabilitybrowser_generate_locatorno sensitive capabilitybrowser_handle_dialogno sensitive capability
Show 28 more tools ↓
browser_hoverno sensitive capabilitybrowser_installno sensitive capabilitybrowser_mouse_click_xyno sensitive capabilitybrowser_mouse_downno sensitive capabilitybrowser_mouse_drag_xyno sensitive capabilitybrowser_mouse_move_xyno sensitive capabilitybrowser_mouse_upno sensitive capabilitybrowser_mouse_wheelno sensitive capabilitybrowser_navigateno sensitive capabilitybrowser_navigate_backno sensitive capabilitybrowser_network_requestsno sensitive capabilitybrowser_pdf_saveno sensitive capabilitybrowser_press_keyno sensitive capabilitybrowser_resetno sensitive capabilitybrowser_resizeno sensitive capabilitybrowser_select_optionno sensitive capabilitybrowser_sessionno sensitive capabilitybrowser_snapshotno sensitive capabilitybrowser_start_tracingno sensitive capabilitybrowser_stop_tracingno sensitive capabilitybrowser_tabsno sensitive capabilitybrowser_take_screenshotno sensitive capabilitybrowser_typeno sensitive capabilitybrowser_verify_element_visibleno sensitive capabilitybrowser_verify_list_visibleno sensitive capabilitybrowser_verify_text_visibleno sensitive capabilitybrowser_verify_valueno sensitive capabilitybrowser_wait_forno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (38 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, 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 |
|---|---|---|---|---|
v0.1.4 latest |
A 92/100 | 7 | 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 playwriter-browser-mcp --onlineMore 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