io.github.4hmetuyar/memory-poisoning-scanner
Scans agent code for untrusted input poisoning persistent cross-session memory
Servidor MCP · de 4hmetuyar
Resumen
io.github.4hmetuyar/memory-poisoning-scanner es un servidor MCP publicado por 4hmetuyar. 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 2026-10-15.
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-memory-poisoning-scanner (@guardbee/mcp-memory-poisoning-scanner en npm)
- Descargas de npm por semana: 210 (2026-10-12)
- Descargas de npm por mes: 782 (2026-10-12)
- Última versión en npm: 0.1.3, publicada el 2026-10-11
- La versión declarada 0.1.2 no figura en npm
- La versión declarada 0.1.3 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 memory-poisoning-scanner -- npx -y @guardbee/mcp-memory-poisoning-scanner[mcp_servers.memory-poisoning-scanner]
command = "npx"
args = ["-y", "@guardbee/mcp-memory-poisoning-scanner"]{
"mcpServers": {
"memory-poisoning-scanner": {
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-memory-poisoning-scanner"
]
}
}
}Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 0.1.2 | Descargas por mes (npm): 782 Descargas por semana (npm): 210 Forks (GitHub): 1 Estrellas (GitHub): 1 |
Sin marca | |
| Official MCP Registry (Abrir el registro) | Publicado | 0.1.3 | 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
- Otra ficha de Official MCP Registry se unió a este producto
- Official MCP Registry: apareció
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.
-
tool-poisoning-scanner io.github.4hmetuyar/tool-poisoning-scanner
Scans MCP tool definitions for hidden instructions and confused-deputy sinks
-
mcp-server-auditor io.github.4hmetuyar/mcp-server-auditor
Scans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets
-
mcpshield io.github.MCPShield-Dev/mcpshield
Security scanner for MCP servers - detects tool poisoning and injection
-
Tripwire Guard — evidence-first injection scanner
Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.
-
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
-
ai-code-scanner io.github.4hmetuyar/ai-code-scanner
Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
-
codesafer io.github.goldmembrane/codesafer
Scans AI-generated code for invisible Unicode, Trojan Source, and supply-chain threats.
-
heimdall io.github.caglarbozkurt/heimdall
Scan an MCP server or agent config for injection, exfiltration, and risky capabilities.
-
toxic-flow-auditor io.github.4hmetuyar/toxic-flow-auditor
Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress
-
OWASP threat scanner auditing codebases for safety leaks.
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…
-
Dependency security guard for AI coding agents. Automatically scans npm, pip, pnpm, yarn, and bun packages for known vulnerabilities and malicious code before installation using…
-
npm-postinstall-attack-scanner
Detect npm supply chain attacks that use the postinstall + hidden dependency pattern to deliver malware. Built in response to the axios maintainer account takeover (2026-03-31…
-
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…
-
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.
Publicado en Claude Code: claude-plugins-official (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…
-
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…
-
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
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…
-
MCP server for terminal commands, file operations, and process management
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…
-
Inspect recent issues and events in Sentry from Codex.
-
Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
Publicado en Community GitHub marketplaces (5)
-
Local-first defensive scanner for vulnerable dependencies, leaked secrets, and risky agent configs
-
Check npm/PyPI packages exist and that a function or method exists in an exact package version.
-
blast-scope io.github.Atharva-Jayappa/blast-scope
Contextual blast-radius scoring for shell commands an AI agent is about to run
-
Passive security scanner: audits MCP servers against the OWASP MCP Top 10, graded A-F.
-
calllint io.github.calllint/calllint
Static preflight safety gate for MCP servers — scan configs before you run them. Never executes.
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Triage Dependabot alerts and recommend safe, evidence-based dependency updates.
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
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…
-
Complete toolkit for building Model Context Protocol (MCP) servers in Kotlin using the official io.modelcontextprotocol:kotlin-sdk library. Includes instructions for best…
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Advanced Security plugin for GitHub Copilot.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into 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.
-
Navigate and interact with your C++ code using the Microsoft C++ Language Server.
Publicado en Cursor: cursor/plugins (5)
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Scaffold and validate new agent plugins.
-
Let Grok Bot reach MCP servers on your private Tailscale network. Sign in to Tailscale to connect your tailnet; Grok Bot joins it as one tagged device and only reaches the hosts…
-
Build apps, scripts, and automations with the TypeScript SDK.
-
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
Publicado en Docker MCP Catalog (5)
-
A comprehensive security scanner for MCP servers with YARA rules and static analysis capabilities.
-
npm-sentinel-mcp io.github.Nekzus/npm-sentinel-mcp
Advanced NPM analysis: Recursive security scanning, ecosystem awareness, and deep insights.
-
stackhawk com.stackhawk/stackhawk
An MCP server that provides interaction with StackHawk's security scanning platform.
-
Analyze code quality and security with SonarQube Server or Cloud directly in AI assistants.
-
MCP server for using Semgrep to scan code for security vulnerabilities.
Publicado en Official MCP Registry (5)
-
tool-poisoning-scanner io.github.4hmetuyar/tool-poisoning-scanner
Scans MCP tool definitions for hidden instructions and confused-deputy sinks
-
mcp-server-auditor io.github.4hmetuyar/mcp-server-auditor
Scans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets
-
mcpshield io.github.MCPShield-Dev/mcpshield
Security scanner for MCP servers - detects tool poisoning and injection
-
Tripwire Guard — evidence-first injection scanner
Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.
-
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
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.