Aletheia Runtime Safety & Scope Creep Filter
Deterministic pre-execution filter that blocks known scope-creep and prompt-injection tool calls
Servidor MCP · de vikasny30
Resumen
Aletheia Runtime Safety & Scope Creep Filter es un servidor MCP publicado por vikasny30. Marketplaces que leemos y que lo publican: 1 (Official MCP Registry). El último cambio que registramos fue el 2026-10-19. Según nuestra pasada por los marketplaces del 2026-10-23.
Qué pide
- Se ejecuta en tu equipo
- Secretos: 1
- Ajustes: 4
Requiere: ALETHEIA_OPERATOR_SECRET (secreta)
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 aletheia-mcp (aletheia-mcp en npm)
- Descargas de npm por semana: 32 (2026-10-19)
- Descargas de npm por mes: 204 (2026-10-19)
- Última versión en npm: 0.3.1, publicada el 2026-09-12
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
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 --env "ALETHEIA_OPERATOR_SECRET=<YOUR_ALETHEIA_OPERATOR_SECRET>" --transport stdio aletheia-mcp -- npx -y aletheia-mcp[mcp_servers.aletheia-mcp]
command = "npx"
args = ["-y", "aletheia-mcp"]
[mcp_servers.aletheia-mcp.env]
ALETHEIA_OPERATOR_SECRET = "<YOUR_ALETHEIA_OPERATOR_SECRET>"{
"mcpServers": {
"aletheia-mcp": {
"command": "npx",
"args": [
"-y",
"aletheia-mcp"
],
"env": {
"ALETHEIA_OPERATOR_SECRET": "<YOUR_ALETHEIA_OPERATOR_SECRET>"
}
}
}
}Sustituya los valores entre corchetes angulares por los suyos. Mostramos los nombres de los ajustes, nunca valores.
Argumentos opcionales que también declara: --allow-write, --allow-network, --allow-loopback, --allowed-paths.
Ajustes opcionales que también indica: ALETHEIA_ALLOW_LOOPBACK, ALETHEIA_ALLOW_NETWORK, ALETHEIA_ALLOW_WRITE.
Dónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir el registro) | Publicado | 0.3.1 | Descargas por mes (npm): 204 Descargas por semana (npm): 32 Forks (GitHub): 0 Estrellas (GitHub): 12 |
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 prompts, tool definitions and model output for injection, and guard agent tool calls.
-
promptrejectormcp io.github.revsmoke/promptrejectormcp
Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.
-
agent-guardrail io.github.rudimentall1/agent-guardrail
Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.
-
mcp-seatbelt io.github.KryptosAI/mcp-seatbelt
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
-
guardrails io.github.ExpertVagabond/guardrails
AI Agent Guardrails MCP server - security layer
-
mcp-server io.github.ingressward/mcp-server
Block prompt injection, evasive spacing, and obscene content before it reaches your LLM.
-
injectshield io.github.bch1212/injectshield
Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.
-
Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
-
Classifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.
-
zenable app.zenable/zenable
Zenable cleans up sloppy AI code and prevents vulnerabilities with deterministic guardrails
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)
-
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…
-
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.
-
Security guardrails for Claude Code. Intercepts every tool call via PreToolUse hook and evaluates it against your Open Agent Passport (OAP) policy before execution. Blocks…
-
VerifiedX helps Claude install and verify action protection in existing AI systems with minimal code changes. It inspects a repo, detects the smallest real integration seam such…
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
-
Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple markdown files.
-
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…
-
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…
-
Semgrep catches security vulnerabilities in real-time and guides Claude to write secure code from the start.
Publicado en Claude: knowledge-work-plugins (5)
-
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…
-
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…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
MCP server for terminal commands, file operations, and process management
-
Hosted MCP server for AI-assisted Grafana Cloud observability — no local installation required.
Publicado en Codex: openai-curated (openai/plugins) (5)
-
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…
-
Codex Security workflows for security scans, analysis, and investigation.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
Publicado en Community GitHub marketplaces (5)
-
protect-mcp com.scopeblind/protect-mcp
Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
-
Checks every tool call, tool output and reply with TypeSafe's Jev model: prompt-injection screening, approval gating and secret scrubbing.
-
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.
-
Runtime security hooks: CLAUDE.md injection scanner (SessionStart) + Bash prompt injection detector (PreToolUse)
-
AI-powered tool use validation using LLM backends (Vertex AI, etc.) to evaluate command safety and correctness
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
-
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…
-
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…
-
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.
-
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…
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
Publicado en Cursor: cursor/plugins (5)
-
Query and remediate compliance tests, controls, frameworks, risks, and vulnerabilities in Vanta.
-
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…
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
Publicado en Docker MCP Catalog (5)
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
-
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.
Publicado en Official MCP Registry (5)
-
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
-
promptrejectormcp io.github.revsmoke/promptrejectormcp
Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.
-
agent-guardrail io.github.rudimentall1/agent-guardrail
Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.
-
mcp-seatbelt io.github.KryptosAI/mcp-seatbelt
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
-
guardrails io.github.ExpertVagabond/guardrails
AI Agent Guardrails MCP server - security layer
Publicado en npm registry (MCP servers) (5)
-
protect-mcp com.scopeblind/protect-mcp
Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
-
guardvibe io.github.goklab/guardvibe
Deterministic security layer your AI can't be. 618 rules, 39 tools, CLI + doctor + host audit.
-
speclock io.github.sgroy10/speclock
AI Constraint Engine — enforces CLAUDE.md and .cursorrules as laws. 51 MCP tools.
-
mcp com.dechonet/mcp
30 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.
-
Audit MCP servers for tool poisoning, rug pulls and supply-chain risk (OWASP MCP Top 10).
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.