Agent Security Scanner MCP Server

by mikehzp Your server? Claim it

local only

Agent Security Scanner runs on your own machine — the client starts it, so there is no endpoint to ping. 113 installs a week from pypi.

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

Installs per day peak 63 · avg 23 · -14% w/w

a month agotoday

113

Installs / week

pypi · agentvuln

—

Stars

on GitHub

—

Last commit

0 releases in 90 days

—

License

language unknown

Nothing serious here today

Today is the operative word: we check Agent Security Scanner every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agentvuln -- uvx agentvuln

~/Library/Application Support/Claude/claude_desktop_config.json

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

~/.codex/config.toml

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

.cursor/mcp.json

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

.vscode/mcp.json

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

Alternatives to Agent Security Scanner

same job, measured the same way

Promptrejectormcp

by revsmoke

Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.

24 installs/wk local only

Agent Security Scanner MCP

by sinewaveai

Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.

728 installs/wk local only

SecurityScan

by apisecurityscan

Scan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.

8 tools answering

AIShield Security Scanner

by lm203688

Scans MCP servers for tool poisoning, prompt injection and supply chain risks.

46 installs/wk 9 tools local only

MCP Safeguard

by cognivators

MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.

125 installs/wk local only

Shadowgate MCP

by josephibra

Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.

answering

Bawbel Scanner

by bawbel

Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.

176 installs/wk local only

Bawbel Scanner

by bawbel

Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.

local only

Agent Security Scanner — questions

Answers built from our own checks of this server.

Why is there no uptime for Agent Security Scanner?

Agent Security Scanner runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package agentvuln was installed 113 times last week.

How do I connect Agent Security Scanner?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls agentvuln straight from pypi; nothing to host, nothing to sign up for.

How many people use Agent Security Scanner?

The pypi package agentvuln was installed 113 times in the last week. Week over week that is -14%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.