Server data from the Official MCP Registry
AI-native browser runtime for autonomous agents with human-in-the-loop supervision
AI-native browser runtime for autonomous agents with human-in-the-loop supervision
Unverified package source
We couldn't verify that the installable package matches the reviewed source code. Proceed with caution.
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-unmodeled-tyler-vessel-browser": {
"args": [
"-y",
"@quanta-intellect/vessel-browser"
],
"command": "npx"
}
}
}The MCP server has good authentication patterns using environment variables and implements reasonable security practices, but contains several medium-severity vulnerabilities including unsafe HTML manipulation, dynamic code execution via executeJavaScript, and insufficient input sanitization that could lead to security issues in browser automation contexts. Package verification found 1 issue (1 critical, 0 high severity).
Scanned 3 files · 6 findings
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Be the first to review this server!