AgentDiet A2A Indirect Prompt-Injection & Jailbreak Firewall
Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections an.
Servidor MCP · de agentdiet.dev
Resumen
AgentDiet A2A Indirect Prompt-Injection & Jailbreak Firewall es un servidor MCP publicado por agentdiet.dev. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). Lo vimos por primera vez el 2026-10-19 y desde entonces no hemos registrado cambios. Según nuestra pasada por los marketplaces del 2026-10-20.
Qué pide
- Se ejecuta en remoto
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.
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 remoto
Generado a partir de lo que declara Official MCP Registry.
claude mcp add --transport http prompt-guard https://prompt-guard.agentdiet.dev/mcp[mcp_servers.prompt-guard]
url = "https://prompt-guard.agentdiet.dev/mcp"{
"mcpServers": {
"prompt-guard": {
"url": "https://prompt-guard.agentdiet.dev/mcp"
}
}
}Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 7.0.15 | Sin cifra publicada | 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
- Pasó a ser un producto que seguimos
- Official MCP Registry: apareció
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.
-
Check text before your agent reads it: hidden instructions, invisible text and links that leak data.
-
Prompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.
-
AI safety scanning, PII detection, prompt injection defense, and adaptive threat learning
-
AI skill security scanner. Detects prompt injection, credential theft, ClawHavoc. Free, no signup.
-
Scan text, documents, websites, and MCP metadata for prompt injection and sensitive-data risks.
-
cloakcheck app.vercel.cloakcheck-wheat/cloakcheck
Scan a page for hidden prompt-injection payloads targeting AI agents.
-
Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
-
Email safety MCP server. Detects phishing, prompt injection, CEO fraud for AI agents.
-
Prompt-injection detector for untrusted text before it reaches an LLM (RU/EN). BYO lovec.tech key.
-
Tripwire Guard — evidence-first injection scanner
Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.
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)
-
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…
-
Security audit plugin that scans Claude Code skills, hooks, and MCP configurations for threats. Detects 37 attack patterns including prompt injection, data exfiltration, supply…
-
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.
-
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…
-
LGBTQIA+ safety tools for LLM engineers — audit prompts, review code, and catch harms before you ship
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…
-
Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple markdown files.
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
-
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…
-
Semgrep catches security vulnerabilities in real-time and guides Claude to write secure code from the start.
Publicado en Claude: knowledge-work-plugins (5)
-
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…
-
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…
-
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…
-
The complete web toolkit for your agent. Search the web and get answers in milliseconds. Fetch any URL and get clean markdown content back. Send a browser agent to navigate sites…
-
Query the StackHawk platform API for security posture reporting, findings analysis, and app management. Guides agents through authentication, data retrieval, and result…
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)
-
AI safety scanning, PII detection, prompt injection defense, and adaptive threat learning
-
AI agent security guard. Blocks dangerous commands, prevents data leaks, protects secrets.
-
AI threat modeling, prompt injection testing, and LLM security hardening.
-
AI-powered tool use validation using LLM backends (Vertex AI, etc.) to evaluate command safety and correctness
-
AI Guard and AI-EDR security controls for coding agents, powered by Trajectory
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.
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Triage Dependabot alerts and recommend safe, evidence-based dependency updates.
-
Visualizes live session AI-credit usage as a Pac-Man board with pellets, ghosts, fruit milestones, and game-over limits.
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
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.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
Build and manage Microsoft Dataverse solutions using natural language. Includes table/column creation, solution lifecycle, data operations, and MCP server configuration.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
Publicado en Cursor: cursor/plugins (5)
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Browse and automate the web with TinyFish: run multi-step web automations, search the web, extract clean page content, and drive remote stealth browser sessions.
-
playwright-mcp io.github.microsoft/playwright-mcp
Playwright Tools for MCP
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Enrich people and companies, run AI research agents.
Publicado en Docker MCP Catalog (5)
-
Real-time web search, reasoning, and research through Perplexity's API
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Production-ready RAG service to search and retrieve data from your documents.
-
npm-sentinel-mcp io.github.Nekzus/npm-sentinel-mcp
Advanced NPM analysis: Recursive security scanning, ecosystem awareness, and deep insights.
-
stackhawk com.stackhawk/stackhawk
An MCP server that provides interaction with StackHawk's security scanning platform.
Publicado en Official MCP Registry (5)
-
Check text before your agent reads it: hidden instructions, invisible text and links that leak data.
-
Prompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.
-
AI skill security scanner. Detects prompt injection, credential theft, ClawHavoc. Free, no signup.
-
Scan text, documents, websites, and MCP metadata for prompt injection and sensitive-data risks.
-
cloakcheck app.vercel.cloakcheck-wheat/cloakcheck
Scan a page for hidden prompt-injection payloads targeting AI agents.
Publicado en npm registry (MCP servers) (5)
-
mcp com.dechonet/mcp
30 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.
-
CVE, KEV, EPSS, SBOM and advisory lookups; per-CVE exposure from Shodan data (© Shodan). Keyless.
-
Local persistent memory and Markdown wiki for AI coding agents: 24 MCP tools, no gateway required.
-
Read-only MCP server exposing the dsh-plugin-certification registry for DeepSeek Harness plugins.
-
Uptime monitoring for developers — monitors, incidents, heartbeats, maintenance, status pages
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.
¿Quieres esta marca para tu plugin en nuestro catálogo?
Demuestra que lo mantienes con un archivo en su repositorio, un archivo en tu dominio o un registro DNS, y podrás mostrar esta marca en la ficha, con banners en vivo para tu web y tu README. Cómo funciona la verificación
Además 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.