io.github.4hmetuyar/tool-poisoning-scanner
Scans MCP tool definitions for hidden instructions and confused-deputy sinks
Servidor MCP · de 4hmetuyar
Resumen
io.github.4hmetuyar/tool-poisoning-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 2026-10-16.
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-tool-poisoning-scanner (@guardbee/mcp-tool-poisoning-scanner en npm)
- Descargas de npm por semana: 1 050 (2026-10-16)
- Descargas de npm por mes: 1 660 (2026-10-16)
- Última versión en npm: 0.2.13, publicada el 2026-10-15
- La versión declarada 0.2.14 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 tool-poisoning-scanner -- npx -y @guardbee/mcp-tool-poisoning-scanner[mcp_servers.tool-poisoning-scanner]
command = "npx"
args = ["-y", "@guardbee/mcp-tool-poisoning-scanner"]{
"mcpServers": {
"tool-poisoning-scanner": {
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-tool-poisoning-scanner"
]
}
}
}Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 0.2.1 | Descargas por mes (npm): 1 660 Descargas por semana (npm): 1 050 Forks (GitHub): 1 Estrellas (GitHub): 1 |
Sin marca | |
| Official MCP Registry (Abrir el registro) | Publicado | 0.2.14 | Descargas por mes (npm): 1 660 Descargas por semana (npm): 1 050 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 0.2.14 (antes 0.2.13)
- Official MCP Registry: publicó la versión 0.2.13 (antes 0.2.11)
- Official MCP Registry: publicó la versión 0.2.11 (antes 0.2.10)
- Official MCP Registry: publicó la versión 0.2.10 (antes 0.2.9)
- Official MCP Registry: publicó la versión 0.2.9 (antes 0.2.8)
- Official MCP Registry: publicó la versión 0.2.8 (antes 0.2.7)
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.
-
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
-
memory-poisoning-scanner io.github.4hmetuyar/memory-poisoning-scanner
Scans agent code for untrusted input poisoning persistent cross-session memory
-
A comprehensive security scanner for MCP servers with YARA rules and static analysis capabilities.
-
mcpcheck io.github.joeyough/mcpcheck
Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.
-
toxic-flow-auditor io.github.4hmetuyar/toxic-flow-auditor
Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress
-
MCP Security & Vulnerability Auditor
Static AST security scanner detecting command injection, leaked secrets, and SSRF in MCP tools.
-
heimdall io.github.caglarbozkurt/heimdall
Scan an MCP server or agent config for injection, exfiltration, and risky capabilities.
-
mcp-observatory io.github.KryptosAI/mcp-observatory
MCP security scanner. CI-native testing, attack simulation, health scoring, and SARIF.
-
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)
-
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…
-
Security audit plugin that scans Claude Code skills, hooks, and MCP configurations for threats. Detects 37 attack patterns including prompt injection, data exfiltration, supply…
-
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…
-
latio-secure-supply-chain-skills
Audit and take action to secure your repository against supply chain misconfigurations and malware.
Publicado en Claude Code: claude-plugins-official (5)
-
Semgrep catches security vulnerabilities in real-time and guides Claude to write secure code from the start.
-
Sonatype Guide MCP server for software supply chain intelligence and dependency security. Analyze dependencies for vulnerabilities, get secure version recommendations, and check…
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
-
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…
-
gk-cli com.gitkraken/gk-cli
The GitKraken MCP Server for managing repos, PRs, issues across GitHub, GitLab, Bitbucket and more.
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 repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
-
Inspect recent issues and events in Sentry from Codex.
Publicado en Community GitHub marketplaces (5)
-
Local-first defensive scanner for vulnerable dependencies, leaked secrets, and risky agent configs
-
calllint io.github.calllint/calllint
Static preflight safety gate for MCP servers — scan configs before you run them. Never executes.
-
Passive security scanner: audits MCP servers against the OWASP MCP Top 10, graded A-F.
-
Audit MCP servers for secrets exposure, shell injection, and supply chain risks.
-
Verify an npm or PyPI package before install: advisories, install scripts, typosquats, repository.
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Triage Dependabot alerts and recommend safe, evidence-based dependency updates.
-
Complete toolkit for building Model Context Protocol (MCP) servers in Kotlin using the official io.modelcontextprotocol:kotlin-sdk library. Includes instructions for best…
-
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…
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
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…
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Advanced Security plugin for GitHub Copilot.
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
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.
-
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.
-
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…
-
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.
-
Thermo-nuclear branch review: deep security/correctness audits, harsh code-quality rubrics, parallel subagents, thermos orchestration, and optional merge-ready PR flows.
-
Scaffold and validate new agent plugins.
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.
-
maven-tools-mcp io.github.arvindand/maven-tools-mcp
JVM dependency intelligence for AI assistants via Maven Central
-
Analyze code quality and security with SonarQube Server or Cloud directly in AI assistants.
Publicado en Official MCP Registry (5)
-
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
-
memory-poisoning-scanner io.github.4hmetuyar/memory-poisoning-scanner
Scans agent code for untrusted input poisoning persistent cross-session memory
-
mcpcheck io.github.joeyough/mcpcheck
Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.
-
toxic-flow-auditor io.github.4hmetuyar/toxic-flow-auditor
Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress
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.