VITNA – Containment for rogue AI agents
Guard wraps stdio MCP servers: risky calls wait for a person; no answer, no run. Remote: cooperative
Servidor MCP · de costrinity.xyz
Resumen
VITNA – Containment for rogue AI agents es un servidor MCP publicado por costrinity.xyz. Marketplaces que leemos y que lo publican: 2 (Official MCP Registry, npm registry (MCP servers)). El último cambio que registramos fue el 2026-10-25. Según nuestra pasada por los marketplaces del 2026-10-28.
Qué pide
- Se ejecuta en remoto
- Se ejecuta en tu equipo
- Secretos: 1
- Ajustes: 5
Requiere: VITNA_API_KEY (secreta), cabecera Authorization
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 @costrinity/vitna-compliance-mcp (@costrinity/vitna-compliance-mcp en npm)
- Descargas de npm por semana: 853 (2026-10-15)
- Descargas de npm por mes: 1 557 (2026-10-25)
- Última versión en npm: 0.5.6, publicada el 2026-10-12
Sin vulnerabilidades conocidas en OSV para 0.5.6 (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 remoto
Generado a partir de lo que declara Official MCP Registry.
claude mcp add --transport http vitna-compliance-preflight https://vitna.costrinity.xyz/api/mcp --header "Authorization: Bearer <YOUR_TOKEN>"[mcp_servers.vitna-compliance-preflight]
url = "https://vitna.costrinity.xyz/api/mcp"
http_headers = { "Authorization" = "Bearer <YOUR_TOKEN>" }{
"mcpServers": {
"vitna-compliance-preflight": {
"url": "https://vitna.costrinity.xyz/api/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}Sustituya los valores entre corchetes angulares por los suyos. Mostramos los nombres de los ajustes, nunca valores.
Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 0.5.6 | Descargas por mes (npm): 1 557 Descargas por semana (npm): 853 Forks (GitHub): 0 Estrellas (GitHub): 0 |
Sin marca | |
| npm registry (MCP servers) (Abrir en npm) | Publicado | 0.5.6 | Descargas por mes (npm): 1 557 Descargas por semana (npm): 853 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.
Cómo han cambiado sus cifras
- 2026-10-151,7 mil
- 2026-10-251,6 mil
Cada punto es un día en que leímos un número distinto; los tramos planos son días en que el número no cambió. Las cifras de distintos marketplaces nunca se suman.
Qué cambió
- Official MCP Registry: publicó la versión 0.5.6 (antes 0.5.5)
- Official MCP Registry: cambió la descripción
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.
-
Action-level governance for AI agents -- control what they DO, not what they SAY
-
think-mcp net.agentutil/think-mcp
Intent security pre-flight checks for autonomous AI agents.
-
mcp-process io.github.Digital-Defiance/mcp-process
Process management and monitoring for AI agents with strict security boundaries
-
mcp com.decionis/mcp
Authorize consequential AI agent actions before execution
-
agent-guard io.github.mdfifty50-boop/agent-guard
Constitutional guardrails and loop detection for AI agents
-
agent-gate com.forgeorbital/agent-gate
Local mandate gate and proof trail for AI agents that take consequential actions.
-
vantagate-mcp-server io.github.Aderix/vantagate-mcp-server
VantaGate MCP Server & OpenAPI integration - Human-in-the-Loop for AI Agents
-
agent-firewall-mcp io.github.mlawsonking/agent-firewall-mcp
Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.
-
openglass-mcp io.github.federico2001/openglass-mcp
Look up any AI agent before you act; register, attest actions, run sealed sessions.
-
mgc-blackbox io.github.zkeviny/mgc-blackbox
A trusted local encrypted execution boundary 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)
-
eu-ai-act-compliance-mcp io.github.CSOAI-ORG/eu-ai-act-compliance-mcp
Eu Ai Act Compliance MCP Server by MEOK AI Labs
-
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…
-
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…
-
deepmiro io.github.kakarot-dev/deepmiro
Simulate hundreds of AI agents to predict how communities react to events and policies
-
MCP server that gives AI agents full control of your cmux terminal — run commands, read output, and send control characters. Works in the background via Unix socket with no focus…
Publicado en Claude Code: claude-plugins-official (5)
-
firebase-mcp io.github.firebase/firebase-mcp
Gives AI development tools Firebase-specific capabilities and expertise.
-
mcp-server io.github.cap-js/mcp-server
Model Context Protocol (MCP) server for AI-assisted development of CAP applications.
-
MCP server for terminal commands, file operations, and process management
-
Skills for designing and building MCP servers that work seamlessly with Claude. Guides you through deployment models (remote HTTP, MCPB, local), tool design patterns, auth, and…
-
mdk-mcp-server io.github.SAP/mdk-mcp-server
Model Context Protocol (MCP) server for AI-assisted development of MDK applications.
Publicado en Claude: knowledge-work-plugins (5)
-
MCP server for terminal commands, file operations, and process management
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
-
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…
-
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…
Publicado en Codex: openai-curated (openai/plugins) (5)
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
Publicado en Community GitHub marketplaces (5)
-
Find and fix reliability and safety gaps in agent code, across nine agent SDKs.
-
mcp io.github.seldonframe/mcp
Build, deploy, and sell AI agents for local-service businesses - from your IDE.
-
Self-healing CI tests and proof of work for AI agents
-
yggdrasil io.github.VonderVuflya/yggdrasil
One shared, durable memory for your AI coding agents — local-first, zero-dependency.
-
Local AI studio on your GPU: images, video, music, voice, RAG. Needs the Guaardvark app installed.
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…
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
Complete toolkit for building Model Context Protocol (MCP) servers in TypeScript/Node.js using the official SDK. Includes instructions for best practices, a prompt for generating…
-
Complete toolkit for building Model Context Protocol (MCP) servers in Kotlin using the official io.modelcontextprotocol:kotlin-sdk library. Includes instructions for best…
-
Explore and query TimeBase streams, schemas, QQL, symbols, and server status via MCP.
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
Advanced Security plugin for GitHub Copilot.
-
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…
-
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…
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…
-
Patterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Query and remediate compliance tests, controls, frameworks, risks, and vulnerabilities in Vanta.
Publicado en Docker MCP Catalog (5)
-
Server-enforced workflow discipline for AI agents: work items, dependency graphs, quality gates
-
MCP server for terminal commands, file operations, and process management
-
Discover and connect to a curated marketplace of MCP servers for extending AI agent capabilities.
-
Wayfound’s MCP server allows business users to govern, supervise, and improve AI Agents.
-
Official Arm MCP server for code migration, optimization, and Arm architecture guidance
Publicado en Official MCP Registry (5)
-
Action-level governance for AI agents -- control what they DO, not what they SAY
-
think-mcp net.agentutil/think-mcp
Intent security pre-flight checks for autonomous AI agents.
-
mcp-process io.github.Digital-Defiance/mcp-process
Process management and monitoring for AI agents with strict security boundaries
-
mcp com.decionis/mcp
Authorize consequential AI agent actions before execution
-
agent-guard io.github.mdfifty50-boop/agent-guard
Constitutional guardrails and loop detection for AI agents
Publicado en PyPI (MCP servers) (5)
-
e2b com.mcparmory/e2b
Create and manage secure sandboxes for running AI agent code
-
MCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.
-
Unified MCP server for AgenticLens and Agentic Chaos capabilities.
-
mnemo io.github.n24q02m/mnemo
Persistent AI memory with hybrid search and embedded sync. Open, free, unlimited.
-
Drive a BenchPod hardware-in-the-loop bench: power, flash, UART, I2C, CAN, analog and logic.
Publicado en npm registry (MCP servers) (5)
-
Marrow AI: Control Layer for AI Agents
Approval gate and audit trail for AI agent actions: policy check first, proof after. Any MCP client.
-
KEPTA — the memory for AI systems
Local encrypted memory for AI: hybrid search, 8 MCP tools, one file you own. Free, no cloud.
-
4da-mcp-server io.github.4DA-Systems/4da-mcp-server
Upgrade intelligence for AI agents: what an upgrade changes, where it touches your code, CVE scans.
-
mcp-server-scf app.scfcontrolsplatform/mcp-server-scf
MCP server for the SCF Controls Platform — 187 tools for controls, evidence, risk, and TPRM.
-
MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.
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. Datos de npm registry (MCP servers). 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.