Loading
Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
The publisher's own command. Not a PlugMCP endpoint.
uvx agentvuln==0.4.2
claude mcp add io.github.mikehzp-agentvuln -- uvx agentvuln==0.4.2
Run in a terminal.
{
"mcpServers": {
"io.github.mikehzp-agentvuln": {
"command": "uvx",
"args": [
"agentvuln==0.4.2"
]
}
}
}claude_desktop_config.json
Remote URL or a command on your machine? How the two installs differ
Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
README is not crawled yet. No repository on file.
No tool list yet. Remote servers get one after the first health check.