com.cognivators/mcp-safeguard
MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
Servidor MCP · de cognivators.com
Resumen
com.cognivators/mcp-safeguard es un servidor MCP publicado por cognivators.com. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). Lo vimos por primera vez el 2026-10-11 y desde entonces no hemos registrado cambios. Según nuestra pasada por los marketplaces del 2026-10-21.
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.
Paquete
PyPI mcp-safeguard (mcp-safeguard en PyPI)
- Descargas de PyPI por semana: 111 (2026-10-13)
- Descargas de PyPI por mes: 586 (2026-10-13)
- Última versión en PyPI: 0.9.3, publicada el 2026-09-07
Sin vulnerabilidades conocidas en OSV para 0.3.2 (comprobado el 2026-10-14)
Los datos de PyPI proceden de pypi.org y las descargas de PyPI de pypistats.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 local: paquete PyPI
Generado a partir de lo que declara Official MCP Registry.
claude mcp add --transport stdio mcp-safeguard -- uvx mcp-safeguard[mcp_servers.mcp-safeguard]
command = "uvx"
args = ["mcp-safeguard"]{
"mcpServers": {
"mcp-safeguard": {
"command": "uvx",
"args": [
"mcp-safeguard"
]
}
}
}Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 0.3.2 | Descargas por mes (PyPI): 586 Descargas por semana (PyPI): 111 |
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
Nada ha cambiado en este plugin desde que lo seguimos.
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.
-
Scan for prompt injection, secrets, PII, and vet MCP servers before installation
-
GuardianShield io.github.sparkvibe-io/GuardianShield
AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs
-
Singularity - MCP Discovery & Security Gateway
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
-
mcp dev.safeprompt/mcp
Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.
-
Tripwire Guard — evidence-first injection scanner
Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.
-
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
-
Scans MCP servers for tool poisoning, prompt injection and supply chain risks.
-
promptrejectormcp io.github.revsmoke/promptrejectormcp
Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.
-
mcp-server com.pentest-tools/mcp-server
MCP server for Pentest-Tools.com: run scans, manage findings and reports via your preffered LLM.
-
mcp com.dechonet/mcp
30 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.
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)
-
Security audit plugin that scans Claude Code skills, hooks, and MCP configurations for threats. Detects 37 attack patterns including prompt injection, data exfiltration, supply…
-
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…
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
-
AI-native security intelligence. Query your security posture, investigate threats, triage alerts, and run SQL against all your connected data sources — directly from Claude Code.
Publicado en 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
-
Semgrep catches security vulnerabilities in real-time and guides Claude to write secure code from the start.
-
Skills for working with NightVision, a DAST and API Discovery platform that finds exploitable vulnerabilities in web applications and REST APIs
-
Deep vulnerability scanning of your own code, run entirely inside your Claude Code session at a chosen effort tier, with every finding challenged before it is reported and the…
-
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…
Publicado en Claude: knowledge-work-plugins (5)
-
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…
-
Configure, run, and interpret HawkScan DAST results inside Claude Code. Generates stackhawk.yml configs, runs scans via CLI or Docker, and transforms security findings into…
-
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…
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
Publicado en Codex: openai-curated (openai/plugins) (5)
-
Codex Security workflows for security scans, analysis, and investigation.
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
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)
-
Audit MCP servers for secrets exposure, shell injection, and supply chain risks.
-
Abnormal Security email threats, cases, and reporting in your terminal and your AI agents.
-
AI Guard and AI-EDR security controls for coding agents, powered by Trajectory
-
Agent Detection & Response (ADR) for Claude Code — guards commands, files, and web requests
-
AI agent security guard. Blocks dangerous commands, prevents data leaks, protects secrets.
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Use Datadog directly in Copilot / VS Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation.
-
Triage Dependabot alerts and recommend safe, evidence-based dependency updates.
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Advanced Security plugin for GitHub Copilot.
-
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.
-
Build and manage Microsoft Dataverse solutions using natural language. Includes table/column creation, solution lifecycle, data operations, and MCP server configuration.
-
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…
Publicado en Cursor: cursor/plugins (5)
-
Let Grok Bot reach MCP servers on your private Tailscale network. On your own tailnet it joins as one tag:grokbot device; on your team's company tailnet, turned on by a team…
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
playwright-mcp io.github.microsoft/playwright-mcp
Playwright Tools for MCP
Publicado en Docker MCP Catalog (5)
-
stackhawk com.stackhawk/stackhawk
An MCP server that provides interaction with StackHawk's security scanning platform.
-
npm-sentinel-mcp io.github.Nekzus/npm-sentinel-mcp
Advanced NPM analysis: Recursive security scanning, ecosystem awareness, and deep insights.
-
A comprehensive security scanner for MCP servers with YARA rules and static analysis capabilities.
-
Connects with the Beagle Security backend using a user token to manage applications, run automated security tests, track vulnerabilities across environments, and gain intelligence…
-
Analyze code quality and security with SonarQube Server or Cloud directly in AI assistants.
Publicado en Official MCP Registry (5)
-
Scan for prompt injection, secrets, PII, and vet MCP servers before installation
-
GuardianShield io.github.sparkvibe-io/GuardianShield
AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs
-
Singularity - MCP Discovery & Security Gateway
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
-
mcp dev.safeprompt/mcp
Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.
-
Tripwire Guard — evidence-first injection scanner
Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.
Publicado en npm registry (MCP servers) (5)
-
mcp com.dechonet/mcp
30 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.
-
CVE, KEV, EPSS, SBOM and advisory lookups; per-CVE exposure from Shodan data (© Shodan). Keyless.
-
Read-only MCP server exposing the dsh-plugin-certification registry for DeepSeek Harness plugins.
-
Uptime monitoring for developers — monitors, incidents, heartbeats, maintenance, status pages
-
depwire io.github.atef-ataya/depwire
Dependency graph + 24 MCP tools. Impact analysis, simulation, security, agent coordination
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.