Agent Chrome MCP Server
agent-chrome-mcp
npm
v1.0.36
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 stdio bridge for controlling your own Chrome browser with AI agents
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 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 99 − 8 = 91. 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 10
high Shell/command execution in server code (dist/agent/directory-picker.js)MTC-SRC-002
In the server's implementation (`dist/agent/directory-picker.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: kdialog */ const node_child_process_1 = require("node:child_process"); const node_util_1 = require("node:util"); const
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/agent/directory-picker.js
high Shell/command execution in server code (dist/agent/engines/codex.js)MTC-SRC-002
In the server's implementation (`dist/agent/engines/codex.js:7`): 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: ne = void 0; const node_child_process_1 = require("node:child_process"); const node_readline_1 = __importDefault(require
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/agent/engines/codex.js
high Shell/command execution in server code (dist/agent/open-project.js)MTC-SRC-002
In the server's implementation (`dist/agent/open-project.js:27`): 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: /promises"); const node_child_process_1 = require("node:child_process"); const project_service_1 = require("./project-se
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/agent/open-project.js
medium Dynamic module load from a non-literal (dist/agent/engines/claude.js)MTC-SRC-005
In the server's implementation (`dist/agent/engines/claude.js:68`): 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: n('moduleName', 'return import(moduleName)')(sdkModuleName); query = sdk.query; } catch (err
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/agent/engines/claude.js
low Shell/command execution in packaging/dev tooling (dist/scripts/browser-config.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/scripts/browser-config.js:44`): 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: require("path")); const child_process_1 = require("child_process"); const constant_1 = require("./constant"); var Browse
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/scripts/browser-config.js
low Shell/command execution in packaging/dev tooling (dist/scripts/build.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/scripts/build.js:6`): 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: { value: true }); const child_process_1 = require("child_process"); const fs_1 = __importDefault(require("fs")); const p
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/scripts/build.js
low Shell/command execution in packaging/dev tooling (dist/scripts/doctor.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/scripts/doctor.js:18`): 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: require("path")); const child_process_1 = require("child_process"); const constant_1 = require("./constant"); const brow
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/scripts/doctor.js
low Shell/command execution in packaging/dev tooling (dist/scripts/report.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/scripts/report.js:17`): 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: require("path")); const child_process_1 = require("child_process"); const constant_1 = require("./constant"); const brow
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/scripts/report.js
low Shell/command execution in packaging/dev tooling (dist/scripts/utils.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/scripts/utils.js:23`): 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: t(require("os")); const child_process_1 = require("child_process"); const util_1 = require("util"); const constant_1 = r
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/scripts/utils.js
low Package runs install-time scripts (postinstall)MTC-SUP-010
"agent-chrome-mcp" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.
Evidence: node dist/scripts/postinstall.js
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package agent-chrome-mcp
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 3
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 |
|---|---|---|---|---|
v1.0.36 latest |
A 91/100 | 10 | 1.13.0 | 2026-09-07 |
v1.0.35 |
A 91/100 | 10 | 1.12.1 | 2026-07-27 |
v1.0.34 |
A 91/100 | 10 | 1.10.0 | 2026-07-25 |
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 agent-chrome-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