ActionGuard Protocol Inspector Agent
Diff and poisoning detection for MCP servers: catch schema drift and prompt poisoning.
Servidor MCP · de lsendel
Resumen
ActionGuard Protocol Inspector Agent es un servidor MCP publicado por lsendel. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). El último cambio que registramos fue el 2026-10-26. Según nuestra pasada por los marketplaces del 2026-11-11.
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 actionguard https://actionguard.ai/mcp[mcp_servers.actionguard]
url = "https://actionguard.ai/mcp"{
"mcpServers": {
"actionguard": {
"url": "https://actionguard.ai/mcp"
}
}
}Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 1.0.0 | Forks (GitHub): 1 Estrellas (GitHub): 0 |
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.
Cómo han cambiado sus cifras
- 2026-10-261
- 2026-11-111
Cada punto es un día en que leímos un número distinto; los tramos planos son días en que el número no cambió. Las cifras de distintos marketplaces nunca se suman.
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.
-
Fixzi — MCP & API Schema Drift Monitor
Monitor MCP servers, API contracts and AI outputs for schema drift. Alerts on breaking changes.
-
MCP Trust & Tool-Poisoning Audit
Audit MCP servers for tool poisoning and shadowing. Scan a remote server by URL or paste its tools.
-
Audit AI Agent SDKs and MCP servers for breaking changes, schema drift, and migration fixes.
-
Scan for prompt injection, secrets, PII, and vet MCP servers before installation
-
integration-agent ai.getvda/integration-agent
MCP Drift Observatory: has a public MCP server's declared tools changed? Free check, archive, feeds.
-
Store and compare organization JSON snapshots. No database crawling. Customer key required.
-
Run Scout Monitoring's MCP tools locally with an API key: endpoints, traces, errors, N+1 insights.
-
Scans an MCP server for security gaps before your agent connects. Free tier, no signup.
-
monitor work.agentexchange.tooldrift/monitor
Check if an MCP server tool changed or hides injection patterns before you trust it.
-
SQL pipeline observability and DBT integration monitor.
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)
-
Claude Code plugin for Firetiger observability workflows and MCP-powered investigations.
-
Java profiling with AI agent integration. Profile CPU, memory, JDBC, HTTP and more.
-
AI-native security intelligence. Query your security posture, investigate threats, triage alerts, and run SQL against all your connected data sources — directly from Claude Code.
-
Use Datadog directly in Claude Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation. This plugin is in…
-
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)
-
Dynatrace observability skills: DQL query patterns, application and infrastructure monitoring, log analysis, problem investigation, and incident response workflows, with the…
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
-
Query the StackHawk platform API for security posture reporting, findings analysis, and app management. Guides agents through authentication, data retrieval, and result…
-
Use Datadog directly in Claude Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation. This plugin is in…
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
Publicado en Claude: knowledge-work-plugins (5)
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
-
Official SigNoz plugin for MCP setup, docs, queries, dashboards, and alerts
-
Query the StackHawk platform API for security posture reporting, findings analysis, and app management. Guides agents through authentication, data retrieval, and result…
-
Use Datadog directly in Claude Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation. This plugin is in…
-
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 Codex: openai-curated (openai/plugins) (5)
-
Codex Security workflows for security scans, analysis, and investigation.
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Available for US1 customers only. Analyze, investigate, and act on your Datadog telemetry directly from ChatGPT using natural language. Ask questions about your production…
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Inspect recent issues and events in Sentry from Codex.
Publicado en Community GitHub marketplaces (5)
-
Every runZero query, plus a local SQLite copy of your whole attack surface that diffs over time
-
CLI and MCP server for RocketCyber Managed SOC: triage, MTTR, and posture analytics.
-
Abnormal Security email threats, cases, and reporting in your terminal and your AI agents.
-
Every SentinelOne v2.1 management endpoint, plus an offline SQLite store and cross-entity analytics
-
Every Better Stack Uptime feature, plus an offline SQLite mirror and cross-resource fleet analytics
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Use Datadog directly in Copilot / VS Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation.
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Query Sumo Logic logs, alerts, dashboards, and SIEM insights directly from Copilot.
-
See a live map of the Copilot agents on your computer, their sub-agents, their commands, and where their data goes.
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 Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
Publicado en Cursor: cursor/plugins (4)
-
Query and remediate compliance tests, controls, frameworks, risks, and vulnerabilities in Vanta.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Let Grok Bot reach MCP servers on your private Tailscale network: connect your own tailnet, or your team's company tailnets turned on by a team admin, with each member using their…
-
Work with PostHog from chat: query product analytics and run SQL, manage feature flags and experiments, triage error tracking issues, and review session replays, surveys, and…
Publicado en Docker MCP Catalog (5)
-
stackhawk com.stackhawk/stackhawk
An MCP server that provides interaction with StackHawk's security scanning platform.
-
MCP Server to interact with a SuzieQ network observability instance via its REST API.
-
AI interface to troubleshoot and observe Kubernetes/Container workloads.
-
Real-time network monitoring, security analysis, and firewall management through 28 specialized tools. Access security alerts, network flows, device status, and firewall rules…
-
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
Publicado en Official MCP Registry (5)
-
Fixzi — MCP & API Schema Drift Monitor
Monitor MCP servers, API contracts and AI outputs for schema drift. Alerts on breaking changes.
-
MCP Trust & Tool-Poisoning Audit
Audit MCP servers for tool poisoning and shadowing. Scan a remote server by URL or paste its tools.
-
Audit AI Agent SDKs and MCP servers for breaking changes, schema drift, and migration fixes.
-
Scan for prompt injection, secrets, PII, and vet MCP servers before installation
-
integration-agent ai.getvda/integration-agent
MCP Drift Observatory: has a public MCP server's declared tools changed? Free check, archive, feeds.
Publicado en PyPI (MCP servers) (5)
-
Incident management, on-call scheduling, and intelligent analysis powered by Rootly.
-
mcp-safeguard com.cognivators/mcp-safeguard
MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
-
Sniff out what your AI tools are hiding: local security checks for MCP servers (hidden instructions, known malware, leaked secrets, rug pulls).
-
Guard Core security MCP: SecurityConfig validation, docs search, live threat detection.
-
Scan, enumerate, and risk-score every MCP server configured on your machine.
Publicado en npm registry (MCP servers) (5)
-
agent-security-scanner-mcp io.github.sinewaveai/agent-security-scanner-mcp
Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
-
infra-lens-mcp io.github.oaslananka/infra-lens-mcp
SSH Linux metrics, baselines, anomaly detection, and plain-English infrastructure explanations.
-
ai-agent-firewall com.fidacy/ai-agent-firewall
Every agent action watched, every money-moving one gated, every verdict independently verifiable.
-
Ask Vulnify before an AI agent acts. Check, record, and read policy decisions.
-
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
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.