MCP server

Agent Security Scanner

io.github.Mikehzp/agentvuln

Checked 25 Oct 2026, 21:11 UTC · Still published on its registry; checked against OSV.dev; never run by us

Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.

Runs on your computer

At a glance

Type: MCP server
Publisher: Not verified
Status: Runs on your computer
Sets up in: Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code
Last checked: 25 Oct 2026, 21:11 UTC

Connect it to your agent

Add to Cursor Add to VS Code VS Code Insiders

Opens the app, which shows the server and asks you to confirm. It then runs the package on your computer with your permissions. For other apps, copy the setup below.

Claude Code

claude mcp add agentvuln -- uvx agentvuln@0.4.2

Claude Desktop

{"mcpServers":{"agentvuln":{"command":"uvx","args":["agentvuln@0.4.2"]}}}

Codex (config.toml)

[mcp_servers.agentvuln]
command = "uvx"
args = ["agentvuln@0.4.2"]

Gemini CLI

{"mcpServers":{"agentvuln":{"command":"uvx","args":["agentvuln@0.4.2"]}}}

Cursor

{"mcpServers":{"agentvuln":{"command":"uvx","args":["agentvuln@0.4.2"]}}}

VS Code

{"servers":{"agentvuln":{"type":"stdio","command":"uvx","args":["agentvuln@0.4.2"]}}}

Runs on your computer with your permissions: check the package and its source before installing.

Browse

Related MCP servers

Axiom Agentic Tools
x402-paid Base agent tools (USDC). 5 deterministic tools. No API keys. No NFT pass.
ScanLabsAI Security Scanner
Scan a website for vulnerabilities: OWASP Top 10, CVEs, SSL, headers - with plain-English fixes
ShipLatch
Free passive security scan for AI-built apps: leaked API keys, public .env files, security headers
SimplyScan
Security, SEO and AI-visibility scanner for web apps · free scans and focused checks via MCP.
Prompt Injection Scanner
Check text before your agent reads it: hidden instructions, invisible text and links that leak data.
Agent-Shield
Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
Agent Security Scanner
Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
MCPAmpel - MCP Security Scanner
Scan installed MCP servers for security vulnerabilities with 16 detection engines.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.Mikehzp/agentvuln.svg)](https://aptlynx.net/servers/io.github.Mikehzp/agentvuln)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents