io.github.naoanao/safe-agent-mcp
Audit API-key privileges, check idempotency patterns, explain AI-agent guard patterns. Read-only.
Servidor MCP · de naoanao
Resumo
io.github.naoanao/safe-agent-mcp é um servidor MCP publicado por naoanao. Marketplaces que lemos e que o listam: 1 (Official MCP Registry). Vimos pela primeira vez em 2026-10-29 e não registramos mudanças desde então. Conforme nossa passagem pelos marketplaces em 2026-10-31.
O que pede
- Roda na sua máquina
Nenhum dos marketplaces que lemos publica as ferramentas ou as configurações que ele pede.
O que declara, pede e executa, por completo
Instale apenas plugins de desenvolvedores em quem você confia. Mostramos o que os marketplaces publicam e não testamos plugins.
Funciona com
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Um link de um clique abre o cliente, que pede confirmação antes de adicionar o servidor.
Pelos marketplaces que o listam e pelo transporte MCP que declara, conforme cada cliente documenta. Não testamos plugins.
Conectar
Comandos e configurações gerados apenas a partir do que os marketplaces declaram. Não os executamos por você e não testamos plugins.
Como servidor MCP local: pacote PyPI
Gerado a partir do que Official MCP Registry declara.
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"
]
}
}
}Onde está publicado
| Marketplace | Status | Versão | Números | Verificado | Visto pela primeira vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir o registro) | Listado | 0.1.0 | Forks (GitHub): 0 Estrelas (GitHub): 0 |
Sem marcação |
Cada número é do próprio marketplace e nunca é somado entre marketplaces. Um marketplace que não publica números não mostra nenhum: sem número não é zero.
O que mudou
- Passou a ser um produto que acompanhamos
- Official MCP Registry: apareceu
Plugins semelhantes
Produtos cujos próprios nomes, descrições, ferramentas e skills são os mais próximos deste pelo significado, em todos os marketplaces que lemos. A proximidade é ordenada apenas dentro desta 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 semelhantes por marketplace
A mesma pergunta feita a cada marketplace separadamente: existe lá um equivalente deste plugin?
Listado em 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…
Listado em 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
Listado em 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…
Listado em 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…
Listado em 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.
Listado em 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.
Listado em 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.
Listado em 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.
Listado em 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.
Listado em 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.
Listado em 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.
Listado em 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 pelo significado, não por código ou repositório em comum: plugins semelhantes continuam sendo produtos distintos, e isto não é uma avaliação nem uma recomendação.
Quer esta marca no seu plugin em nosso catálogo?
Prove que o mantém com um arquivo no repositório, um arquivo no seu domínio ou um registro DNS, e você poderá mostrar esta marca na ficha, com banners ao vivo para o seu site e o README. Como funciona a verificação
Você também recebe alertas quando um marketplace o publica, o remove, muda a marca de verificado ou o que ele pede, e o endpoint remoto passa a ser monitorado como um serviço web.
Dados de Official MCP Registry. Os números vêm das nossas próprias passagens regulares pelos marketplaces, última leitura em . Não publicamos dados de contato dos editores de plugins.