cdp-tools-mcp
npm
v0.7.3
Source verified
Published by indate — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Connects AI assistants to the Chrome DevTools Protocol for runtime debugging, including breakpoints, variable inspection, network monitoring, and automated browser interactions.
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 − 6 = 72. 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 |
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.
In the server's implementation (`build/utils/modal-detector.js:69`): 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: xt-line no-eval eval(isBasicVisibleFn); // eslint-disable-next-line no-eval eval(isBlockingPosit
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 build/utils/modal-detector.js
The implementation both builds shell commands out of runtime values (`build/server-manager.js`) and evaluates runtime values as code (`build/utils/modal-detector.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
In the server's implementation (`build/utils/modal-detector.js:69`): 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: xt-line no-eval eval(isBasicVisibleFn); // eslint-disable-next-line no-eval eval(isBlockingPosit
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 build/utils/modal-detector.js
In the server's implementation (`build/chrome-launcher.js:5`): 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 * as os from 'os'; import * as path from 'path'; import * as net from 'ne
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 build/chrome-launcher.js
In the server's implementation (`build/runners/docker-compose-runner.js:5`): 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: ort { spawnSync } from 'child_process'; import * as path from 'path'; import * as fs from 'fs'; import { debugLog } from
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 build/runners/docker-compose-runner.js
In the server's implementation (`build/runners/docker-runner.js:5`): 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: ort { spawnSync } from 'child_process'; import { debugLog } from '../debug-logger.js'; /** * Check if Docker is availab
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 build/runners/docker-runner.js
In the server's implementation (`build/runners/native-runner.js:5`): 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 * as fs from 'fs'; import * as path from 'path'; import { debugLog } from
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 build/runners/native-runner.js
In the server's implementation (`build/server-claims.js:49`): 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: { execFileSync } from 'child_process'; import { atomicWriteFile } from './atomic-write.js'; import { getOutputPath } fr
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 build/server-claims.js
In the server's implementation (`build/server-manager.js:786`): 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: nst { exec } = require('child_process'); exec(`lsof -ti :${port}`, (error, stdout) => { if (
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 build/server-manager.js
In the server's implementation (`build/supervisor/child-manager.js:16`): 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'; export class ChildManager { opts; child = null; onExitCallback = nul
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 build/supervisor/child-manager.js
In the server's implementation (`build/supervisor/client-watcher.js:30`): 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: { execFileSync } from 'child_process'; /** * Package managers and shells that are only ever launch plumbing, never the
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 build/supervisor/client-watcher.js
In the server's implementation (`build/tools/screenshot-tools.js:11`): 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 { resolveSelector, isExtendedSelector, cleanupResolvedSelector } from '..
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 build/tools/screenshot-tools.js
In the server's implementation (`build/server-manager.js:787`): 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: _process'); exec(`lsof -ti :${port}`, (error, stdout) => { if (error || !stdout.trim()) {
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 build/server-manager.js
In the server's implementation (`build/helpers/parser-plugins.js:51`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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 mod = await import(url); const plugin = (mod.default ?? mod); if (!plugin || typeof plugin.extract !
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 build/helpers/parser-plugins.js
In a packaging/dev/install script (shipped, but not the server runtime) (`build/tools/storage-tools.test.js:317`): 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 rebuilt = new Function('return (' + describeStructuredValue.toString() + ')')(); const value = { w
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 build/tools/storage-tools.test.js
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 |
|---|---|---|---|---|
v0.7.3 latest |
C 72/100 | 15 | 1.13.0 | 2026-08-25 |
v0.7.2 |
C 72/100 | 15 | 1.12.1 | 2026-08-05 |
v0.7.1 |
C 72/100 | 13 | 1.12.1 | 2026-07-31 |
v0.6.1 |
C 72/100 | 13 | 1.12.1 | 2026-07-29 |
v0.6.0 |
C 72/100 | 13 | 1.12.1 | 2026-07-27 |
v0.5.3 |
C 72/100 | 12 | 1.9.0 | 2026-07-23 |
v0.5.1 |
D 63/100 | 16 | 1.5.0 | 2026-07-22 |
v0.5.0 |
F 58/100 | 17 | 1.4.2 | 2026-07-22 |
v0.4.18 |
D 63/100 | 14 | 1.3.1 | 2026-07-21 |
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.
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 cdp-tools-mcp --online
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