io.github.4hmetuyar/prompt-leak-scanner
Catches leaked credentials and PII in outbound LLM prompts
Servidor MCP · de 4hmetuyar
Resumen
io.github.4hmetuyar/prompt-leak-scanner es un servidor MCP publicado por 4hmetuyar. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). El último cambio que registramos fue el 2026-10-16. Según nuestra pasada por los marketplaces del 2026-10-18.
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
npm @guardbee/mcp-prompt-leak-scanner (@guardbee/mcp-prompt-leak-scanner en npm)
- Descargas de npm por semana: 1 566 (2026-10-16)
- Descargas de npm por mes: 3 006 (2026-10-16)
- Última versión en npm: 0.1.22, publicada el 2026-10-15
- La versión declarada 0.1.23 no figura en npm
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.
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 npm
Generado a partir de lo que declara Official MCP Registry.
claude mcp add --transport stdio prompt-leak-scanner -- npx -y @guardbee/mcp-prompt-leak-scanner[mcp_servers.prompt-leak-scanner]
command = "npx"
args = ["-y", "@guardbee/mcp-prompt-leak-scanner"]{
"mcpServers": {
"prompt-leak-scanner": {
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-prompt-leak-scanner"
]
}
}
}Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 0.1.6 | Descargas por mes (npm): 3 006 Descargas por semana (npm): 1 566 Forks (GitHub): 1 Estrellas (GitHub): 1 |
Sin marca | |
| Official MCP Registry (Abrir el registro) | Publicado | 0.1.23 | Descargas por mes (npm): 3 006 Descargas por semana (npm): 1 566 Forks (GitHub): 1 Estrellas (GitHub): 1 |
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
- Official MCP Registry: publicó la versión 0.1.23 (antes 0.1.22)
- Official MCP Registry: publicó la versión 0.1.22 (antes 0.1.20)
- Official MCP Registry: publicó la versión 0.1.20 (antes 0.1.19)
- Official MCP Registry: publicó la versión 0.1.19 (antes 0.1.18)
- Official MCP Registry: publicó la versión 0.1.18 (antes 0.1.17)
- Official MCP Registry: publicó la versión 0.1.17 (antes 0.1.16)
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.
-
ai-code-scanner io.github.4hmetuyar/ai-code-scanner
Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
-
mcp-safeguard com.cognivators/mcp-safeguard
MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
-
mcp-secret-scrub io.github.sudo-ai-git/mcp-secret-scrub
Deterministic no-LLM MCP server that scrubs secrets before they reach an agent. Never leaks values.
-
Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
-
tracepiishield-mcp com.clauxel.tracepiishield/tracepiishield-mcp
PII scanning and redaction receipts for LLM traces and tool payloads.
-
secrets-audit-mcp io.github.eltociear/secrets-audit-mcp
Detects leaked secrets & API keys: 32+ provider rules (AWS, GitHub, Stripe, OpenAI…), zero deps.
-
leakferret io.github.leakferrethq/leakferret
Context-aware secret scanner: lets an AI agent scan, verify, and rewrite secrets before committing.
-
prompt-guard-mcp io.github.robertoyanguas-ops/prompt-guard-mcp
Scans untrusted web pages, emails, or tool outputs for prompt injections and returns sanitized tex
-
zentric-protocol-mcp io.github.ZentricProtocol/zentric-protocol-mcp
Prompt injection + PII detection for LLM apps and agent pipelines. Deterministic, sub-25ms.
-
GuardianShield io.github.sparkvibe-io/GuardianShield
AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs
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)
-
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…
-
Secure design patterns for Claude Code LLM applications: external content ingestion, endpoint hardening, output validation, system prompt design, and multi-agent action surface…
-
Security audit plugin that scans Claude Code skills, hooks, and MCP configurations for threats. Detects 37 attack patterns including prompt injection, data exfiltration, supply…
-
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…
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
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.
-
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…
-
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…
-
Aikido Security scanning for Claude Code — SAST, secrets, and IaC vulnerability detection powered by the Aikido MCP server.
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…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Query the StackHawk platform API for security posture reporting, findings analysis, and app management. Guides agents through authentication, data retrieval, and result…
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…
-
Available for US1 customers only. Analyze, investigate, and act on your Datadog telemetry directly from ChatGPT using natural language. Ask questions about your production…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
Publicado en Community GitHub marketplaces (2)
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…
-
Automatically enforce SonarQube code quality and security in the agent coding loop — 7,000+ rules, secrets scanning, agentic analysis, and quality gates across 40+ languages…
-
Triage Dependabot alerts and recommend safe, evidence-based dependency updates.
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
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.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
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.
-
Scaffold and validate new agent plugins.
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.
-
Give your AI agents trusted access to the full Postman platform.
-
Analyze code quality and security with SonarQube Server or Cloud directly in AI assistants.
Publicado en Official MCP Registry (5)
-
ai-code-scanner io.github.4hmetuyar/ai-code-scanner
Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
-
mcp-safeguard com.cognivators/mcp-safeguard
MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
-
mcp-secret-scrub io.github.sudo-ai-git/mcp-secret-scrub
Deterministic no-LLM MCP server that scrubs secrets before they reach an agent. Never leaks values.
-
Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
-
tracepiishield-mcp com.clauxel.tracepiishield/tracepiishield-mcp
PII scanning and redaction receipts for LLM traces and tool payloads.
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.