Agent Security Scanner
Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
Servidor MCP · de Mikehzp
Resumen
Agent Security Scanner es un servidor MCP publicado por Mikehzp. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). Lo vimos por primera vez el 2026-10-11 y desde entonces no hemos registrado cambios. Según nuestra pasada por los marketplaces del 2026-10-14.
Qué pide
- Se ejecuta en tu equipo
Ninguno de los marketplaces que leemos publica sus herramientas ni los ajustes que pide.
Lo que declara, pide y ejecuta, completo
Instala solo plugins de desarrolladores en los que confíes. Mostramos lo que publican los marketplaces y no probamos plugins.
Paquete
PyPI agentvuln (agentvuln en PyPI)
- Descargas de PyPI por semana: 32 (2026-10-13)
- Descargas de PyPI por mes: 134 (2026-10-13)
- Última versión en PyPI: 0.4.2, publicada el 2026-06-08
Sin vulnerabilidades conocidas en OSV para 0.4.2 (comprobado el 2026-10-14)
Los datos de PyPI proceden de pypi.org y las descargas de PyPI de pypistats.org. Cada cifra es del propio registro y nunca se suma a otra. Un registro que no publica una cifra no muestra ninguna: sin cifra no es cero. Los registros de vulnerabilidades proceden de OSV.dev (CC BY 4.0) y solo se refieren a la versión declarada; un listado sin versión declarada no recibe respuesta. No analizamos código.
Funciona con
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Un enlace de un clic abre el cliente, que pide confirmación antes de añadir el servidor.
Según los marketplaces que lo listan y el transporte MCP que declara, tal como lo documenta cada cliente. No probamos plugins.
Conectar
Comandos y configuraciones generados solo a partir de lo que declaran sus marketplaces. No los ejecutamos por ti ni probamos plugins.
Como servidor MCP local: paquete PyPI
Generado a partir de lo que declara Official MCP Registry.
claude mcp add --transport stdio agentvuln -- uvx agentvuln[mcp_servers.agentvuln]
command = "uvx"
args = ["agentvuln"]{
"mcpServers": {
"agentvuln": {
"command": "uvx",
"args": [
"agentvuln"
]
}
}
}Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 0.4.2 | Descargas por mes (PyPI): 134 Descargas por semana (PyPI): 32 |
Sin marca |
Cada cifra es del propio marketplace y nunca se suma entre marketplaces. Un marketplace que no publica cifras no muestra ninguna: sin número no es cero.
Qué cambió
Nada ha cambiado en este plugin desde que lo seguimos.
Plugins similares
Productos cuyos propios nombres, descripciones, herramientas y skills son los más cercanos a este por su significado, en todos los marketplaces que leemos. La cercanía se ordena solo dentro de esta lista.
-
Agent Skill & Config Security Audit
Scan AI agent skills and configs for hidden Unicode, prompt injection and exfiltration.
-
Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
-
AI skill security scanner. Detects prompt injection, credential theft, ClawHavoc. Free, no signup.
-
Domain security scanning for AI agents. A-F grades, 8 checks, fix snippets.
-
AgentGuard — security checks for AI agents
Secret, CVE and dependency-vulnerability scanning for AI agents (free, OSV.dev).
-
Zero-config MCP security scanner for AI-generated apps. 25K+ vulnerability patterns.
-
Scans MCP servers for tool poisoning, prompt injection and supply chain risks.
-
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
-
Prompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.
-
Security audit plugin that scans Claude Code skills, hooks, and MCP configurations for threats. Detects 37 attack patterns including prompt injection, data exfiltration, supply…
Plugins similares por marketplace
La misma pregunta a cada marketplace por separado: ¿hay allí un equivalente de este plugin?
Publicado en Claude Code: claude-plugins-community (5)
-
Security audit plugin that scans Claude Code skills, hooks, and MCP configurations for threats. Detects 37 attack patterns including prompt injection, data exfiltration, supply…
-
VerifiedX helps Claude install and verify action protection in existing AI systems with minimal code changes. It inspects a repo, detects the smallest real integration seam such…
-
LLM security for AI coding agents. Protect applications from prompt injection, PII leakage, and data exfiltration. Provides MCP tools for scanning text, redacting PII, and…
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
-
Security auditor for Node.js and Python backend APIs. Four skills cover pre-audit reconnaissance (route graph, auth matrix, invariants), static code audit across the OWASP API…
Publicado en Claude Code: claude-plugins-official (5)
-
Deep vulnerability scanning of your own code, run entirely inside your Claude Code session at a chosen effort tier, with every finding challenged before it is reported and the…
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
-
Semgrep catches security vulnerabilities in real-time and guides Claude to write secure code from the start.
-
Automate API security directly in Claude Code with 42Crunch - automatically audit OpenAPI specs, detect vulnerabilities aligned with OWASP API Security risks (including…
-
Configure, run, and interpret HawkScan DAST results inside Claude Code. Generates stackhawk.yml configs, runs scans via CLI or Docker, and transforms security findings into…
Publicado en Claude: knowledge-work-plugins (5)
-
Configure, run, and interpret HawkScan DAST results inside Claude Code. Generates stackhawk.yml configs, runs scans via CLI or Docker, and transforms security findings into…
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
Query the StackHawk platform API for security posture reporting, findings analysis, and app management. Guides agents through authentication, data retrieval, and result…
-
The Vanta plugin connects Claude Code to Vanta's security and compliance platform through the Vanta MCP server. It combines Vanta's test-specific remediation intelligence with…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
Publicado en Codex: openai-curated (openai/plugins) (5)
-
Codex Security workflows for security scans, analysis, and investigation.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
Publicado en Community GitHub marketplaces (5)
-
Automate API security directly in Claude Code with 42Crunch - automatically audit OpenAPI specs, detect vulnerabilities aligned with OWASP API Security risks (including…
-
Sourcery security findings for AI coding agents: triage and minimal-change remediation via the public Sourcery API (12 MCP tools + skills).
-
Aikido Security scanning for Claude Code — SAST, secrets, and IaC vulnerability detection powered by the Aikido MCP server.
-
Endor Labs AI Plugins (Legacy)
Legacy Claude Code plugin id for Endor Labs Agent Kit workflows.
-
Investigate incidents, review code and execute UAT for release readiness, scan code for vulnerabilities, and run penetration tests with AWS DevOps Agent and AWS Security Agent.
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Triage Dependabot alerts and recommend safe, evidence-based dependency updates.
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Advanced Security plugin for GitHub Copilot.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
Publicado en Cursor: cursor/plugins (5)
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
playwright-mcp io.github.microsoft/playwright-mcp
Playwright Tools for MCP
-
Scaffold and validate new agent plugins.
Publicado en Docker MCP Catalog (5)
-
Connects with the Beagle Security backend using a user token to manage applications, run automated security tests, track vulnerabilities across environments, and gain intelligence…
-
stackhawk com.stackhawk/stackhawk
An MCP server that provides interaction with StackHawk's security scanning platform.
-
MCP server for using Semgrep to scan code for security vulnerabilities.
-
Vectra AI MCP Server - An MCP server that connects AI assistants & agents to the Vectra AI security platform, enabling intelligent threat analysis and automated incident response.
-
npm-sentinel-mcp io.github.Nekzus/npm-sentinel-mcp
Advanced NPM analysis: Recursive security scanning, ecosystem awareness, and deep insights.
Publicado en Official MCP Registry (5)
-
Agent Skill & Config Security Audit
Scan AI agent skills and configs for hidden Unicode, prompt injection and exfiltration.
-
Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
-
AI skill security scanner. Detects prompt injection, credential theft, ClawHavoc. Free, no signup.
-
Domain security scanning for AI agents. A-F grades, 8 checks, fix snippets.
-
AgentGuard — security checks for AI agents
Secret, CVE and dependency-vulnerability scanning for AI agents (free, OSV.dev).
Encontrados por significado, no por código ni repositorio compartidos: los plugins similares siguen siendo productos distintos, y esto no es una reseña ni una recomendación.
¿Es tu plugin?
Añádelo a tus proyectos y demuestra que lo mantienes con un archivo en su repositorio, un archivo en tu dominio o un registro DNS. Recibirás avisos cuando un marketplace lo publique, lo retire, cambie su marca verificada o lo que pide, y su endpoint remoto quedará monitorizado como un servicio web.
Datos de Official MCP Registry. Las cifras proceden de nuestros propios recorridos periódicos por los marketplaces, leída por última vez el . No publicamos datos de contacto de los editores de plugins.