Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/abarrac/mcp-seleniumInstalling this writes the configuration, not the program: `java` runs a file from the repository, so clone it first and make the path in the command match where you put it.
Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/abarrac/mcp-selenium/selenium)<a href="https://agentmods.dev/mcp/abarrac/mcp-selenium/selenium"><img src="https://agentmods.dev/badge/mcp/abarrac/mcp-selenium/selenium/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/abarrac/mcp-selenium/selenium"><img src="https://agentmods.dev/badge/mcp/abarrac/mcp-selenium/selenium.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
selenium scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"selenium": {
"command": "java",
"args": [
"-jar",
"~/.mcp-selenium/mcp-selenium.jar"
],
"env": {
"SELENIUM_HEADLESS": "false",
"SELENIUM_TIMEOUT": "30",
"SELENIUM_BROWSER": "chrome"
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 14 lines scan A bf9bbe4f57cd
selenium is an MCP server published in the GitHub repository abarrac/mcp-selenium (20 stars, last pushed 1y ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other mcp servers, from other repositories
playwright-test
A high-level API to automate web browsers. Runs locally from the playwright npm package.
browser
MCP server "browser" as configured in felipebarcelospro/igniter-js. Launched with npx @playwright/mcp@latest.
playwright-original
Context-efficient Playwright tools for MCP. Runs locally from the @tontoko/fast-playwright-mcp npm package.
expect
Let agents test your code in a real browser. Runs locally from the expect-cli npm package.
cypress-mcp
MCP server "cypress-mcp" as configured in miroslavmyrha/cypress-mcp. Runs locally from the @miroslavmyrha/cypress-mcp npm package.
klyk
OS-level macOS app testing via MCP — native apps, Electron apps, browsers, web pages, system dialogs. Runs locally from the klyk Python package.