Browser Dev Tools MCP Server

mcp-browser-dev-tools npm v0.0.5 Source verified

Published by hinaser — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.

Local server for driving browsers over the Chromium DevTools Protocol and Firefox WebDriver BiDi.

Trust grade
A
100/100
Last scanned
Trust
A · 100/100
How safe the published surface and source look. Deterministic; every point is auditable.
Capability
High
Blast radius if it went rogue — what the server’s tools could reach. Independent of trust.
Coverage
Source
How much the scan could actually inspect. Shallow coverage is stated, never hidden.
A Why this grade

Started at 100 and nothing was deducted: the deterministic scan raised no scored threat in the published surface it inspected. Capability observations and advisory notes are recorded but never lower the score.

Findings 2

high Shell/command execution in server code (src/browser-launch-service.mjs)MTC-SRC-002

In the server's implementation (`src/browser-launch-service.mjs: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: child_process

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-launch-service.mjs

high Shell/command execution in server code (src/serve-bootstrap.mjs)MTC-SRC-002

In the server's implementation (`src/serve-bootstrap.mjs: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: child_process

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/serve-bootstrap.mjs

What this scan could not see

Versions

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.

VersionScoreFindingsEngineScanned
v0.0.5 latest A 100/100 2 1.5.0 2026-07-22

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.

MCP Trust Score: A · 100/100
Markdown (GitHub README)
[![MCP Trust Score](https://mcptrustchecker.com/registry/mcp-browser-dev-tools/badge.svg)](https://mcptrustchecker.com/registry/mcp-browser-dev-tools)
HTML
<a href="https://mcptrustchecker.com/registry/mcp-browser-dev-tools"><img src="https://mcptrustchecker.com/registry/mcp-browser-dev-tools/badge.svg" alt="MCP Trust Score" height="20"></a>
Prefer shields.io styling? Point it at https://mcptrustchecker.com/registry/mcp-browser-dev-tools/badge.json via https://img.shields.io/endpoint?url=…

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 mcp-browser-dev-tools --online

Use the free API → How scoring works

More in Browser Automation