io.github.naoanao/safe-agent-mcp
Audit API-key privileges, check idempotency patterns, explain AI-agent guard patterns. Read-only.
MCP-Server · von naoanao
Überblick
io.github.naoanao/safe-agent-mcp ist ein MCP-Server von naoanao. Marktplätze, die wir lesen und die es listen: 1 (Official MCP Registry). Wir haben es erstmals am 2026-10-29 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-10-31.
Was es abfragt
- Läuft auf Ihrem Rechner
Keiner der Marktplätze, die wir lesen, veröffentlicht seine Tools oder die abgefragten Einstellungen.
Was es deklariert, abfragt und ausführt, vollständig
Installieren Sie nur Plugins von Entwicklern, denen Sie vertrauen. Wir zeigen, was die Marktplätze veröffentlichen, und testen keine Plugins.
Funktioniert mit
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Ein Ein-Klick-Link öffnet den Client, der vor dem Hinzufügen des Servers um Bestätigung bittet.
Nach den Marktplätzen, die ihn listen, und dem angegebenen MCP-Transport, wie jeder Client sie dokumentiert. Wir testen keine Plugins.
Verbinden
Befehle und Konfigurationen nur aus den Angaben der Marktplätze. Wir führen sie nicht für Sie aus und testen keine Plugins.
Als lokaler MCP-Server: PyPI-Paket
Erstellt aus den Angaben von 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"
]
}
}
}Wo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Official MCP Registry (Eintrag in der Registry öffnen) | Gelistet | 0.1.0 | Forks (GitHub): 0 Sterne (GitHub): 0 |
Nicht markiert |
Jede Zahl stammt vom jeweiligen Marktplatz und wird nie über Marktplätze hinweg addiert. Ein Marktplatz ohne veröffentlichte Zahl zeigt keine: keine Zahl ist nicht null.
Was sich geändert hat
- Wird seitdem als Produkt geführt
- Official MCP Registry: erschienen
Ähnliche Plugins
Produkte, deren eigene Namen, Beschreibungen, Werkzeuge und Skills diesem der Bedeutung nach am nächsten sind, auf allen Marktplätzen, die wir lesen. Die Nähe ist nur innerhalb dieser Liste geordnet.
-
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.
Ähnliche Plugins nach Marktplatz
Dieselbe Frage an jeden Marktplatz einzeln: Gibt es dort ein Gegenstück zu diesem Plugin?
Gelistet auf 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…
Gelistet auf 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
Gelistet auf 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…
Gelistet auf 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…
Gelistet auf 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.
Gelistet auf 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.
Gelistet auf 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.
Gelistet auf 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.
Gelistet auf 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.
Gelistet auf 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.
Gelistet auf 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.
Gelistet auf 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.
Nach Bedeutung gefunden, nicht über gemeinsamen Code oder ein gemeinsames Repository: Ähnliche Plugins bleiben getrennte Produkte, und dies ist weder eine Bewertung noch eine Empfehlung.
Möchten Sie dieses Zeichen für Ihr Plugin in unserem Katalog?
Belegen Sie mit einer Datei im Repository, einer Datei auf Ihrer Domain oder einem DNS-Eintrag, dass Sie es pflegen, und Sie können dieses Zeichen auf der Karte zeigen, dazu Live-Banner für Ihre Website und Ihr README. So funktioniert die Verifizierung
Außerdem erhalten Sie Hinweise, wenn ein Marktplatz es aufnimmt, entfernt, sein Verified-Zeichen oder seine Anforderungen ändert, und sein Remote-Endpunkt wird wie ein Webdienst überwacht.
Daten von Official MCP Registry. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.