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/EndymionLee/PilotBrowseMCPWrote 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/endymionlee/pilotbrowsemcp/ccprojectdir-browser-mcp)<a href="https://agentmods.dev/mcp/endymionlee/pilotbrowsemcp/ccprojectdir-browser-mcp"><img src="https://agentmods.dev/badge/mcp/endymionlee/pilotbrowsemcp/ccprojectdir-browser-mcp.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
browser-mcp 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 8d 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
{
"browser-mcp": {
"command": "node",
"args": [
"BrowserPlugin\\server\\dist\\index.js"
],
"lifecycle": "keep-alive",
"idleTimeout": 0
}
}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.
- 8d ago First seen · 10 lines scan A 45b8d28b93ef
browser-mcp is an MCP server published in the GitHub repository EndymionLee/PilotBrowseMCP (100 stars, last pushed 1mo 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
chrome-bridge
Your real, logged-in Chrome as an MCP server: 60 token-efficient web-dev tools. ChromeOS included. Runs locally from the chrome-bridge-mcp npm package.
cws
MCP server for Chrome Web Store — extension upload, publish, status, and rollout. Runs locally from the cws-mcp npm package. Needs 3 environment variables to run.
better-ai-browser-utilities
MCP server "better-ai-browser-utilities" as configured in ItMeDiaTech/better-ai-browser-utilities. Runs locally from the better-ai-browser-utilities Python package.
chrome-actuator
MCP server "chrome-actuator" as configured in xlreon/chrome-actuator. Runs ${GROK_PLUGIN_ROOT}/../host/dist/mcp.js with node.
mcp-server
Run Scrapeer visual web-scraping flows from AI agents. Runs locally from the @scrapeer/mcp-server npm package. Needs 1 environment variable to run.
safari-mcp
Native Safari browser automation for AI agents — 80 tools, zero Chrome overhead. Runs locally from the safari-mcp npm package.