Selenium (mrgolfprat) MCP Server
@mrgolfprat/mcp-selenium
npm
v0.1.23
Published by @mrgolfprat — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
Selenium WebDriver MCP Server Custom
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 − 8 = 92. 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 2
high Shell/command execution in server code (bin/mcp-selenium.js)MTC-SRC-002
In the server's implementation (`bin/mcp-selenium.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'; const __filename = fileURLToPath(import.meta.url); const __dirname = dirname
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 bin/mcp-selenium.js
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([get_page_source]) co-exist with external-action tools ([upload_file]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [get_page_source] → sinks [upload_file]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow get_page_source → upload_file
Tools 18
Each tool and what it can reach — statically extracted from the published source.
get_page_sourceingests untrusted inputupload_filenetwork egressclick_elementno sensitive capabilityclose_sessionno sensitive capabilitydouble_clickno sensitive capabilitydrag_and_dropno sensitive capabilityfind_elementno sensitive capabilityget_current_urlno sensitive capabilityget_element_textno sensitive capabilityhoverno sensitive capability
Show 8 more tools ↓
navigateno sensitive capabilitypress_keyno sensitive capabilityrefresh_browserno sensitive capabilityright_clickno sensitive capabilitysend_keysno sensitive capabilitysleepno sensitive capabilitystart_browserno sensitive capabilitytake_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 (18 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 |
|---|---|---|---|---|
v0.1.23 latest |
A 92/100 | 2 | 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 @mrgolfprat/mcp-selenium --onlineOther implementations of Selenium 14
Independent packages implementing the same tool, scanned with the same engine. Compare all 15 side by side →
Production-ready MCP server integrating Selenium 4 (BiDi) for browser automation
Selenium WebDriver MCP Server
Selenium WebDriver Model Context Protocol (MCP) server enabling AI agents and LLMs to control browsers
Selenium WebDriver MCP Server (rayven122 fork — adds Edge IE mode)
Selenium-based automation with 39 tools covering navigation, clicks, typing, assertions, screenshots, multi-session use, and page snapshots with stable element references and batched execution.
Selenium MCP server for browser automation, team-ready, MCP-compliant, and easy to share like Playwright MCP.
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