io.github.naoanao/safe-agent-mcp
Audit API-key privileges, check idempotency patterns, explain AI-agent guard patterns. Read-only.
Servidor MCP · de naoanao
Resumen
io.github.naoanao/safe-agent-mcp es un servidor MCP publicado por naoanao. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). Lo vimos por primera vez el 2026-10-29 y desde entonces no hemos registrado cambios. Según nuestra pasada por los marketplaces del 2026-10-31.
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.
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 safe-agent-mcp -- uvx safe-agent-mcp[mcp_servers.safe-agent-mcp]
command = "uvx"
args = ["safe-agent-mcp"]{
"mcpServers": {
"safe-agent-mcp": {
"command": "uvx",
"args": [
"safe-agent-mcp"
]
}
}
}Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 0.1.0 | Forks (GitHub): 0 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.
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.
-
ai-agent-firewall com.fidacy/ai-agent-firewall
Every agent action watched, every money-moving one gated, every verdict independently verifiable.
-
guardrails io.github.ExpertVagabond/guardrails
AI Agent Guardrails MCP server - security layer
-
agentguard io.tooloracle/agentguard
AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.
-
mcp-gateway io.github.titus-civic/mcp-gateway
Identity, authorization, audit trails, and revocable permissions for AI agents accessing MCP tools.
-
protect-mcp com.scopeblind/protect-mcp
Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
-
Ask Vulnify before an AI agent acts. Check, record, and read policy decisions.
-
gateway ai.sealgate/gateway
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
-
agents com.obsmetrics.paygent/agents
Pay-per-call safety guards for AI agents: injection, tool-call, signing, secret, x402-trust.
-
AgentSecurityLens MCP Security Trust Check
MCP security trust-check for agents before installing MCPs, Skills or tools.
-
Local OpenAPI contract and breaking-change checks for AI agents.
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)
-
Secure MCP servers with OAuth 2.1, token introspection, dynamic client registration, and CIMD so AI agents can call your MCP tools with verified identities
-
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…
-
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…
-
agent-discover io.github.keshrath/agent-discover
Find, install and enable MCP servers mid-session on any host, with consent and tool pinning
-
SCOPE - Security, Compliance & Operational Policy Evaluation - A Claude plugin that runs deterministic pre-flight compliance evaluation on agentic workflows. Maps every MCP tool…
Publicado en Claude Code: claude-plugins-official (5)
-
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.
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
-
Dynatrace observability skills: DQL query patterns, application and infrastructure monitoring, log analysis, problem investigation, and incident response workflows, with the…
-
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…
-
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
-
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…
-
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…
-
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)
-
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…
-
Codex Security workflows for security scans, analysis, and investigation.
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
-
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)
-
Two MCP audits. audit scores the tool definitions of a server you build against MCP-specification, Anthropic tool-design, and Claude-Code client criteria in a per-tool…
-
Abnormal Security email threats, cases, and reporting in your terminal and your AI agents.
-
Build agents, MCP servers and tool-using workflows.
-
One system around coding agents to run, verify, recover, and hand off software work.
-
Audit MCP servers for secrets exposure, shell injection, and supply chain risks.
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Interactive GitHub Copilot canvas for discovering, connecting, and managing hosted MCP servers from an Azure Connector Namespace.
-
crowdstrike-charlotte-ai-agentworks
CrowdStrike Charlotte AI AgentWorks skills for creating, managing, and invoking AI agents via external Falcon API Gateway endpoints. Includes agent lifecycle management…
-
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.
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
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.
-
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…
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
Publicado en Cursor: cursor/plugins (5)
-
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…
-
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.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Scaffold and validate new agent plugins.
Publicado en Docker MCP Catalog (5)
-
Give your AI agents trusted access to the full Postman platform.
-
A unified MCP proxy that aggregates multiple MCP servers into one interface, enabling seamless tool discovery and management across all your AI interactions. Manage all your MCP…
-
stackhawk com.stackhawk/stackhawk
An MCP server that provides interaction with StackHawk's security scanning platform.
-
Wayfound’s MCP server allows business users to govern, supervise, and improve AI Agents.
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
Publicado en Official MCP Registry (5)
-
ai-agent-firewall com.fidacy/ai-agent-firewall
Every agent action watched, every money-moving one gated, every verdict independently verifiable.
-
guardrails io.github.ExpertVagabond/guardrails
AI Agent Guardrails MCP server - security layer
-
agentguard io.tooloracle/agentguard
AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.
-
mcp-gateway io.github.titus-civic/mcp-gateway
Identity, authorization, audit trails, and revocable permissions for AI agents accessing MCP tools.
-
protect-mcp com.scopeblind/protect-mcp
Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
Publicado en PyPI (MCP servers) (5)
-
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.
-
Scan, enumerate, and risk-score every MCP server configured on your machine.
-
Unified MCP server for AgenticLens and Agentic Chaos capabilities.
-
Incident management, on-call scheduling, and intelligent analysis powered by Rootly.
Publicado en npm registry (MCP servers) (5)
-
ai-agent-firewall com.fidacy/ai-agent-firewall
Every agent action watched, every money-moving one gated, every verdict independently verifiable.
-
protect-mcp com.scopeblind/protect-mcp
Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
-
Ask Vulnify before an AI agent acts. Check, record, and read policy decisions.
-
security-proxy io.github.4hmetuyar/security-proxy
MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
-
agent-security-scanner-mcp io.github.sinewaveai/agent-security-scanner-mcp
Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
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.