io.github.MukundaKatta/agentguard
Network-egress firewall for agent tools: check URLs against a declarative policy.
Servidor MCP · de MukundaKatta
Resumen
io.github.MukundaKatta/agentguard es un servidor MCP publicado por MukundaKatta. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). El último cambio que registramos fue el 2026-10-17. Según nuestra pasada por los marketplaces del 2026-10-24.
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
npm @mukundakatta/agentguard-mcp (@mukundakatta/agentguard-mcp en npm)
- Descargas de npm por semana: 28 (2026-10-17)
- Descargas de npm por mes: 134 (2026-10-17)
- Última versión en npm: 0.1.0, publicada el 2026-04-27
Sin vulnerabilidades conocidas en OSV para 0.1.0 (comprobado el 2026-10-23)
Los datos de npm proceden del registro público de npm (registry.npmjs.org, api.npmjs.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 npm
Generado a partir de lo que declara Official MCP Registry.
claude mcp add --transport stdio agentguard -- npx -y @mukundakatta/agentguard-mcp[mcp_servers.agentguard]
command = "npx"
args = ["-y", "@mukundakatta/agentguard-mcp"]{
"mcpServers": {
"agentguard": {
"command": "npx",
"args": [
"-y",
"@mukundakatta/agentguard-mcp"
]
}
}
}Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 0.1.0 | Descargas por mes (npm): 134 Descargas por semana (npm): 28 Forks (GitHub): 0 Estrellas (GitHub): 1 |
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-guard io.github.ipezygj/agent-guard
Safety checks an agent runs before it acts: package malware, destructive command, secret leak.
-
agent-firewall-mcp io.github.mlawsonking/agent-firewall-mcp
Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.
-
shadowgate-mcp io.github.josephibra/shadowgate-mcp
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
-
mnki-mcp io.github.MNKIAgentOS/mnki-mcp
MCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs.
-
agent-guards io.github.mlawsonking/agent-guards
All six agent guard suites in one local MCP server, with optional cloud intelligence.
-
IntentFence Agent Action Firewall
Fail-closed action authorization, MCP risk scanning, x402 checks, and signed receipts.
-
MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.
-
agentguard io.tooloracle/agentguard
AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.
-
agent-guard-mcp io.github.liminalpepe/agent-guard-mcp
Verify-before-act safety checks for AI agents: packages, lockfiles, manifests, CI workflows.
-
MCP security gateway that wraps any MCP server with per-tool policies, Ed25519-signed decision receipts, and human approval gates. Shadow mode (default) logs every tool call…
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)
-
MCP security gateway that wraps any MCP server with per-tool policies, Ed25519-signed decision receipts, and human approval gates. Shadow mode (default) logs every tool call…
-
agent-discover io.github.keshrath/agent-discover
Find, install and enable MCP servers mid-session on any host, with consent and tool pinning
-
Real-time security filter for MCP tool communications. Works as a Claude Code hook to inspect all data sent to and received from MCP servers. Detects prompt injection, API key…
-
nodebench io.github.HomenShum/nodebench
260 MCP tools across 49 domains. AI Flywheel, quality gates, research, web scraping.
-
agent-comm io.github.keshrath/agent-comm
Agent intercommunication - messaging, channels, shared state, and real-time events
Publicado en Claude Code: claude-plugins-official (5)
-
Operational skill for installing, configuring, operating, and debugging CrowdSec (cscli, LAPI/CAPI, hub, bouncers, WAF/AppSec) across bare-metal, Docker, and Kubernetes.
-
Manage Zscaler Zero Trust Exchange via 400+ tools — ZPA, ZIA, ZDX, ZCC, ZTW, ZMS, EASM, and more.
-
firebase-mcp io.github.firebase/firebase-mcp
Gives AI development tools Firebase-specific capabilities and expertise.
-
Connect Claude to a private MCP server through an Anthropic MCP tunnel. The /create-docker-mcp-tunnel command drives the Docker Compose quickstart end to end: certificates, proxy…
-
Detect an MCP server's language (Python, TypeScript or Go) and instrument it with the matching Pendo SDK so MCP tool calls flow into Pendo Agent Analytics.
Publicado en Claude: knowledge-work-plugins (5)
-
Fastly development tools and platform skills
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
-
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…
-
Official SigNoz plugin for MCP setup, docs, queries, dashboards, and alerts
-
gk-cli com.gitkraken/gk-cli
The GitKraken MCP Server for managing repos, PRs, issues across GitHub, GitLab, Bitbucket and more.
Publicado en Codex: openai-curated (openai/plugins) (5)
-
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…
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
-
Codex Security workflows for security scans, analysis, and investigation.
-
Available for US1 customers only. Analyze, investigate, and act on your Datadog telemetry directly from ChatGPT using natural language. Ask questions about your production…
Publicado en Community GitHub marketplaces (5)
-
protect-mcp com.scopeblind/protect-mcp
Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
-
Security-enhanced MCP proxy with policy controls and recovery tools
-
WatchGuard Cloud Firebox, Endpoint Security, ThreatSync, NDR and AuthPoint APIs for every customer
-
Find and fix reliability and safety gaps in agent code, across nine agent SDKs.
-
Offline, rule-based security checks for your repo, dependencies, AI agent config and local app.
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Complete toolkit for building Model Context Protocol (MCP) servers in Go using the official github.com/modelcontextprotocol/go-sdk. Includes instructions for best practices, a…
-
See a live map of the Copilot agents on your computer, their sub-agents, their commands, and where their data goes.
-
Complete toolkit for building Model Context Protocol (MCP) servers in Kotlin using the official io.modelcontextprotocol:kotlin-sdk library. Includes instructions for best…
-
Three-agent workflow for orchestrated software delivery with an orchestrator plus implementation and QA subagents.
-
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.
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
power-automate
Build, edit, run, and debug Power Automate cloud flows via the FlowAgent MCP server — connection lifecycle, surgical edits, copy across environments, run management, and validated…
-
Microsoft Dataverse plugin for coding agents, covering record CRUD, bulk data operations, advanced queries, schema and metadata, administration, security, environment management…
Publicado en Cursor: cursor/plugins (5)
-
Let Grok Bot reach MCP servers on your private Tailscale network. On your own tailnet it joins as one tag:grokbot device; on your team's company tailnet, turned on by a team…
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Query and remediate compliance tests, controls, frameworks, risks, and vulnerabilities in Vanta.
-
Scaffold and validate new agent plugins.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
Publicado en Docker MCP Catalog (5)
-
stackhawk com.stackhawk/stackhawk
An MCP server that provides interaction with StackHawk's security scanning platform.
-
A comprehensive security scanner for MCP servers with YARA rules and static analysis capabilities.
-
Dynatrace-mcp io.github.dynatrace-oss/Dynatrace-mcp
[DEPRECATED] Dynatrace MCP Server. Migrate to dynatrace-for-ai or Dynatrace Remote MCP Server.
-
npm-sentinel-mcp io.github.Nekzus/npm-sentinel-mcp
Advanced NPM analysis: Recursive security scanning, ecosystem awareness, and deep insights.
-
Manage Zscaler Zero Trust Exchange via 400+ tools — ZPA, ZIA, ZDX, ZCC, ZTW, ZMS, EASM, and more.
Publicado en Official MCP Registry (5)
-
agent-guard io.github.ipezygj/agent-guard
Safety checks an agent runs before it acts: package malware, destructive command, secret leak.
-
agent-firewall-mcp io.github.mlawsonking/agent-firewall-mcp
Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.
-
shadowgate-mcp io.github.josephibra/shadowgate-mcp
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
-
mnki-mcp io.github.MNKIAgentOS/mnki-mcp
MCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs.
-
agent-guards io.github.mlawsonking/agent-guards
All six agent guard suites in one local MCP server, with optional cloud intelligence.
Publicado en PyPI (MCP servers) (5)
-
MCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.
-
Guard Core security MCP: SecurityConfig validation, docs search, live threat detection.
-
mcp-safeguard com.cognivators/mcp-safeguard
MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
-
Policy enforcement plane for MCP: every tool call ends in a verdict. Self-hosted, MIT.
-
altr-mcp-server io.github.altrsoftware/altr-mcp-server
MCP server for ALTR data security: databases, tags, policies, classification, access, audits
Publicado en npm registry (MCP servers) (5)
-
protect-mcp com.scopeblind/protect-mcp
Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
-
mcp com.dechonet/mcp
30 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.
-
guardvibe io.github.goklab/guardvibe
Deterministic security layer your AI can't be. 618 rules, 39 tools, CLI + doctor + host audit.
-
mcp-ssh-manager io.github.bvisible/mcp-ssh-manager
SSH server management for agents, with per-server read-only and allowlist security modes
-
Audit MCP servers for tool poisoning, rug pulls and supply-chain risk (OWASP MCP Top 10).
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.