Agent Browser (minhlucvan) MCP Server
agent-browser-mcp
npm
v0.1.3
Published by minhlucvan — 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.
MCP server integrating with Vercel's agent-browser for AI-driven browser automation
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 − 7 = 93. 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 3
high Shell/command execution in server code (dist/tools/executor.js)MTC-SRC-002
In the server's implementation (`dist/tools/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"; // Environment variable for agent-browser executable path const AGENT_BROWSER_PA
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/executor.js
low Shell/command execution in packaging/dev tooling (tests/executor.test.ts)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/executor.test.ts: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: wn = vi.fn(); vi.mock("child_process", () => ({ spawn: mockSpawn, })); // Helper to create mock process functio
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 tests/executor.test.ts
low Shell/command execution in packaging/dev tooling (tests/integration.test.ts)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/integration.test.ts:25`): 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: wn = vi.fn(); vi.mock("child_process", () => ({ spawn: mockSpawn, })); describe("Integration Tests", () => {
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 tests/integration.test.ts
Tools 34
Each tool and what it can reach — statically extracted from the published source.
browser_checkno sensitive capabilitybrowser_clear_cookiesno sensitive capabilitybrowser_clickno sensitive capabilitybrowser_close_sessionno sensitive capabilitybrowser_evaluateno sensitive capabilitybrowser_fillno sensitive capabilitybrowser_get_attributeno sensitive capabilitybrowser_get_consoleno sensitive capabilitybrowser_get_cookiesno sensitive capabilitybrowser_get_htmlno sensitive capability
Show 24 more tools ↓
browser_get_networkno sensitive capabilitybrowser_get_textno sensitive capabilitybrowser_get_titleno sensitive capabilitybrowser_get_urlno sensitive capabilitybrowser_go_backno sensitive capabilitybrowser_go_forwardno sensitive capabilitybrowser_hoverno sensitive capabilitybrowser_is_checkedno sensitive capabilitybrowser_is_enabledno sensitive capabilitybrowser_is_visibleno sensitive capabilitybrowser_navigateno sensitive capabilitybrowser_new_sessionno sensitive capabilitybrowser_pdfno sensitive capabilitybrowser_pressno sensitive capabilitybrowser_reloadno sensitive capabilitybrowser_screenshotno sensitive capabilitybrowser_scrollno sensitive capabilitybrowser_selectno sensitive capabilitybrowser_set_cookiesno sensitive capabilitybrowser_snapshotno sensitive capabilitybrowser_typeno sensitive capabilitybrowser_uncheckno sensitive capabilitybrowser_wait_for_navigationno sensitive capabilitybrowser_wait_for_selectorno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (34 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 |
|---|---|---|---|---|
v0.1.3 latest |
A 93/100 | 3 | 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 agent-browser-mcp --onlineOther implementations of Agent Browser 2
Independent packages implementing the same tool, scanned with the same engine. Compare all 3 side by side →
MCP server integrating with Vercel's agent-browser for AI-driven browser automation
MCP server for agent-browser - complete browser automation with token-efficient @ref system
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