io.github.4hmetuyar/memory-poisoning-scanner
Scans agent code for untrusted input poisoning persistent cross-session memory
Servidor MCP · de 4hmetuyar
Resumo
io.github.4hmetuyar/memory-poisoning-scanner é um servidor MCP publicado por 4hmetuyar. Marketplaces que lemos e que o listam: 1 (Official MCP Registry). Vimos pela primeira vez em 2026-10-11 e não registramos mudanças desde então. Conforme nossa passagem pelos marketplaces em 2026-10-15.
O que pede
- Roda na sua máquina
Nenhum dos marketplaces que lemos publica as ferramentas ou as configurações que ele pede.
O que declara, pede e executa, por completo
Instale apenas plugins de desenvolvedores em quem você confia. Mostramos o que os marketplaces publicam e não testamos plugins.
Pacote
npm @guardbee/mcp-memory-poisoning-scanner (@guardbee/mcp-memory-poisoning-scanner no npm)
- Downloads do npm por semana: 210 (2026-10-12)
- Downloads do npm por mês: 782 (2026-10-12)
- Última versão no npm: 0.1.3, publicada em 2026-10-11
- A versão declarada 0.1.2 não consta no npm
- A versão declarada 0.1.3 não consta no npm
Os dados do npm vêm do registro público do npm (registry.npmjs.org, api.npmjs.org). Cada número é do próprio registro e nunca é somado a outro. Um registro que não publica um número não mostra nenhum: sem número não é zero.
Funciona com
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Um link de um clique abre o cliente, que pede confirmação antes de adicionar o servidor.
Pelos marketplaces que o listam e pelo transporte MCP que declara, conforme cada cliente documenta. Não testamos plugins.
Conectar
Comandos e configurações gerados apenas a partir do que os marketplaces declaram. Não os executamos por você e não testamos plugins.
Como servidor MCP local: pacote npm
Gerado a partir do que Official MCP Registry declara.
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"
]
}
}
}Onde está publicado
| Marketplace | Status | Versão | Números | Verificado | Visto pela primeira vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir o registro) | Listado | 0.1.2 | Downloads por mês (npm): 782 Downloads por semana (npm): 210 Forks (GitHub): 1 Estrelas (GitHub): 1 |
Sem marcação | |
| Official MCP Registry (Abrir o registro) | Listado | 0.1.3 | Forks (GitHub): 1 Estrelas (GitHub): 1 |
Sem marcação |
Cada número é do próprio marketplace e nunca é somado entre marketplaces. Um marketplace que não publica números não mostra nenhum: sem número não é zero.
O que mudou
- Outra listagem em Official MCP Registry passou a fazer parte deste produto
- Official MCP Registry: apareceu
Plugins semelhantes
Produtos cujos próprios nomes, descrições, ferramentas e skills são os mais próximos deste pelo significado, em todos os marketplaces que lemos. A proximidade é ordenada apenas dentro desta 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 semelhantes por marketplace
A mesma pergunta feita a cada marketplace separadamente: existe lá um equivalente deste plugin?
Listado em 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.
Listado em 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
Listado em 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
Listado em 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.
Listado em 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.
Listado em 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…
Listado em 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.
Listado em 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.
Listado em 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.
Listado em 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 pelo significado, não por código ou repositório em comum: plugins semelhantes continuam sendo produtos distintos, e isto não é uma avaliação nem uma recomendação.
Este plugin é seu?
Adicione-o aos seus projetos e prove que o mantém com um arquivo no repositório, um arquivo no seu domínio ou um registro DNS. Você recebe alertas quando um marketplace o publica, o remove, muda a marca de verificado ou o que ele pede, e o endpoint remoto passa a ser monitorado como um serviço web.
Dados de Official MCP Registry. Os números vêm das nossas próprias passagens regulares pelos marketplaces, última leitura em . Não publicamos dados de contato dos editores de plugins.