Browser Agent (akshay2604) MCP Server
mcp-browser-agent
npm
v0.2.1
Published by akshay2604 — 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.
Gives AI agents structured perception of web pages — a semantic UI tree, actions, and linting — via Playwright and the Chrome DevTools Protocol.
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 4
high Tool "ui_watch" exposes command/code executionMTC-CAP-001
Tool "ui_watch" appears to run shell commands or evaluate code (parameter "command"). 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 ui_watch
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([ui_state]) co-exist with external-action tools ([ui_watch]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [ui_state] → sinks [ui_watch]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow ui_state → ui_watch
medium Unconstrained command parameter "command" on "ui_watch"MTC-CAP-006
Tool "ui_watch" takes a command-shaped parameter "command" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool ui_watch · inputSchema.properties.command
low Mutating tool "ui_watch" declares no destructiveHintMTC-CAP-005
Tool "ui_watch" 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 ui_watch
Tools 14
Each tool and what it can reach — statically extracted from the published source.
ui_stateingests untrusted inputui_watchruns code / shellbrowser-agent-guideno sensitive capabilityui_actno sensitive capabilityui_connectno sensitive capabilityui_lintno sensitive capabilityui_locateno sensitive capabilityui_navigateno sensitive capabilityui_observeno sensitive capabilityui_peekno sensitive capability
Show 4 more tools ↓
ui_record_startno sensitive capabilityui_record_stopno sensitive capabilityui_save_sessionno sensitive capabilityui_screenshotno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (14 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 |
|---|---|---|---|---|
v0.2.1 latest |
A 93/100 | 4 | 1.13.0 | 2026-08-25 |
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 mcp-browser-agent --onlineOther implementations of Browser Agent 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
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