@shivdev/agent-warden
A firewall for AI agents. Detects and blocks prompt injection in email, web pages, documents and MCP tool results before they reach your model.
Servidor MCP · de @shivdev
Resumo
@shivdev/agent-warden é um servidor MCP publicado por @shivdev. Marketplaces que lemos e que o listam: 1 (npm registry (MCP servers)). A última mudança que registramos foi em 2026-10-31. Conforme nossa passagem pelos marketplaces em 2026-11-02.
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.
Pacote
npm @shivdev/agent-warden (@shivdev/agent-warden no npm)
- Downloads do npm por semana: 2 852 (2026-10-13)
- Downloads do npm por mês: 3 203 (2026-10-31)
- Última versão no npm: 0.5.0, publicada em 2026-10-19
Os dados do npm vêm do registro público do npm (registry.npmjs.org, api.npmjs.org). Cada número é do próprio registro e nunca é somado a outro. Um registro que não publica um número não mostra nenhum: sem número não é zero.
Conectar
Sem dados para um comando automático: o que os marketplaces declaram não diz de forma inequívoca como conectá-lo.
Onde está publicado
| Marketplace | Status | Versão | Números | Verificado | Visto pela primeira vez |
|---|---|---|---|---|---|
| npm registry (MCP servers) (Abrir no npm) | Listado | 0.5.0 | Downloads por mês (npm): 3 203 Downloads por semana (npm): 2 852 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
- npm registry (MCP servers): lançou a versão 0.5.0 (antes 0.4.4)
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.
-
Multi-agent LLM security layer detecting prompt injection and jailbreaks.
-
Imperium MCP Security — Prompt-Injection, Jailbreak & Tool Poisoning Firewall
Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
-
agent-prompt-injection-firewall-mcp io.github.CSOAI-ORG/agent-prompt-injection-firewall-mcp
The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
-
Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
-
Open-source AI context firewall for governed model, retrieval, memory, and tool access.
-
Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
-
Free pre-action policy checks and data cleaning for autonomous AI agents.
-
Prompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.
-
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
-
promptrejectormcp io.github.revsmoke/promptrejectormcp
Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.
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)
-
Use Claude Code without fear of data leakage. Unbound enforces command policies, DLP and jailbreak guardrails, and streams session analytics to your security dashboard — all with…
-
LLM security for AI coding agents. Protect applications from prompt injection, PII leakage, and data exfiltration. Provides MCP tools for scanning text, redacting PII, and…
-
VerifiedX helps Claude install and verify action protection in existing AI systems with minimal code changes. It inspects a repo, detects the smallest real integration seam such…
-
Compliance-first LLM gateway for Claude Code. Policy-as-code enforcement (YAML policy definitions), tamper-evident audit trails, PII redaction, token budget enforcement, and…
-
Security guardrails for Claude Code. Intercepts every tool call via PreToolUse hook and evaluates it against your Open Agent Passport (OAP) policy before execution. Blocks…
Listado em Claude Code: claude-plugins-official (5)
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
-
Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple markdown files.
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Automate API security directly in Claude Code with 42Crunch - automatically audit OpenAPI specs, detect vulnerabilities aligned with OWASP API Security risks (including…
Listado em Claude: knowledge-work-plugins (5)
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
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…
-
Query the StackHawk platform API for security posture reporting, findings analysis, and app management. Guides agents through authentication, data retrieval, and result…
-
Connects Claude Code to the Synthflow AI voice-agent platform through its hosted MCP server, with skills for reviewing calls and auditing agent prompts, plus a docs-search…
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…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Codex Security workflows for security scans, analysis, and investigation.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
Listado em Community GitHub marketplaces (5)
-
AI agent security guard. Blocks dangerous commands, prevents data leaks, protects secrets.
-
AI safety scanning, PII detection, prompt injection defense, and adaptive threat learning
-
AI Guard and AI-EDR security controls for coding agents, powered by Trajectory
-
Sentinel AI - Safety Guardrails
Real-time safety guardrails for LLM applications. Scans for prompt injection, PII leaks, harmful content, toxicity, hallucinations, and dangerous tool calls with sub-millisecond…
-
Agent Detection & Response (ADR) for Claude Code — guards commands, files, and web requests
Listado em Copilot CLI: github/awesome-copilot (5)
-
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…
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Skills and interactive Copilot canvas for designing, configuring, testing and deploying agents to Microsoft Foundry.
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.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
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)
-
Query and remediate compliance tests, controls, frameworks, risks, and vulnerabilities in Vanta.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
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…
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Browse and automate the web with TinyFish: run multi-step web automations, search the web, extract clean page content, and drive remote stealth browser sessions.
Listado em Docker MCP Catalog (5)
-
Give your AI agents trusted access to the full Postman 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.
-
Documentation on AgentCore platform services.
-
Production-ready RAG service to search and retrieve data from your documents.
Listado em Official MCP Registry (5)
-
Multi-agent LLM security layer detecting prompt injection and jailbreaks.
-
Imperium MCP Security — Prompt-Injection, Jailbreak & Tool Poisoning Firewall
Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
-
agent-prompt-injection-firewall-mcp io.github.CSOAI-ORG/agent-prompt-injection-firewall-mcp
The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
-
Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
-
Open-source AI context firewall for governed model, retrieval, memory, and tool access.
Listado em PyPI (MCP servers) (5)
-
mcp-safeguard com.cognivators/mcp-safeguard
MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
-
air-blackbox-mcp io.github.airblackbox/air-blackbox-mcp
EU AI Act compliance scanner for Python AI agents. 14 tools across 6 articles.
-
Guard Core security MCP: SecurityConfig validation, docs search, live threat detection.
-
Security middleware for MCP. Blocks prompt injection, PII leakage, and resource exhaustion.
-
MCP server for Google Cloud Armor WAF log patrol: deny summaries and false-positive checks
Listado em 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.
-
ai-agent-firewall com.fidacy/ai-agent-firewall
Every agent action watched, every money-moving one gated, every verdict independently verifiable.
-
Evidence-backed AppSec for AI applications and agents. Powered by HAIEC.
-
privacyscrubber-mcp io.github.moxno/privacyscrubber-mcp
Zero-Trust PII & secrets sanitizer for AI agents with in-memory local redaction.
-
security-proxy io.github.4hmetuyar/security-proxy
MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
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 npm registry (MCP servers). Os números vêm das nossas próprias passagens regulares pelos marketplaces, última leitura em . Não publicamos dados de contato dos editores de plugins.