⚠️ Este repositorio se ha movido. El desarrollo activo continúa en ScopeBlind/scopeblind-gateway.
Este fork personal puede estar desactualizado respecto al repositorio canónico. Por favor, utilice el repositorio de la organización para problemas, solicitudes de extracción (pull requests) y el código más reciente.
Puerta de enlace de seguridad para servidores MCP. Registros en modo sombra por defecto, políticas por herramienta, recibos locales opcionales con Ed25519 y salida de auditoría fácil de verificar.
Ruta actual de la CLI: envuelve cualquier servidor MCP stdio como un proxy transparente. En modo sombra, registra cada solicitud tools/call y permite que todo pase. Añada un archivo de política para aplicar reglas por herramienta. Ejecute protect-mcp init para generar claves de firma locales y configuración, de modo que la puerta de enlace también pueda emitir recibos firmados.
# Wrap an existing OpenClaw / MCP config into a usable pack
npx @scopeblind/passport wrap --runtime openclaw --config ./openclaw.json --policy email-safe
# Shadow mode — log every tool call, enforce nothing
npx protect-mcp -- node my-server.js
# Generate keys + config template for local signing
npx protect-mcp init
# Shadow mode with local signing enabled
npx protect-mcp --policy protect-mcp.json -- node my-server.js
# Enforce mode
npx protect-mcp --policy protect-mcp.json --enforce -- node my-server.js
# Export an offline-verifiable audit bundle
npx protect-mcp bundle --output audit.jsonRelated MCP server: protect-mcp
protect-mcp se sitúa entre su cliente MCP y el servidor como un proxy stdio:
MCP Client ←stdin/stdout→ protect-mcp ←stdin/stdout→ your MCP serverIntercepta las solicitudes JSON-RPC tools/call y:
Modo sombra (por defecto): registra cada llamada a herramienta y permite que todo pase
Modo de cumplimiento: aplica reglas de política por herramienta como block, rate_limit y min_tier
Firma local opcional: cuando la firma está configurada, emite un recibo firmado con Ed25519 junto con el registro estructurado
Todos los demás mensajes MCP (initialize, tools/list, notificaciones) pasan de forma transparente.
Políticas por herramienta — bloquee herramientas destructivas, limite la tasa de las costosas y adjunte requisitos de nivel mínimo
Registros de decisión estructurados — cada decisión se emite a stderr con [PROTECT_MCP]
Recibos locales firmados opcionales — generados cuando se ejecuta con una política que contiene signing.key_path, guardados en .protect-mcp-receipts.jsonl y expuestos en http://127.0.0.1:9876/receipts
Verificación sin conexión — verifique recibos o paquetes con npx @veritasacta/verify
No se requiere cuenta — claves locales, política local, proceso local
Esto es importante antes de implementar esto o hablar con los usuarios:
La firma no es automática en la ruta básica npx protect-mcp -- .... Esa ruta registra decisiones en modo sombra. Para la firma local, ejecute npx protect-mcp init y luego inicie la puerta de enlace con el archivo de política generado.
Las comprobaciones de política conscientes del nivel están activas, pero la admisión de manifiestos no está conectada a la ruta CLI/stdio por defecto. La CLI establece las sesiones como unknown a menos que una integración de host llame a la API de admisión mediante programación.
La configuración de credenciales actualmente valida las referencias de credenciales respaldadas por variables de entorno y registra etiquetas de credenciales en registros/recibos. La inyección genérica por llamada en herramientas stdio arbitrarias es específica del adaptador y no la realiza la ruta de proxy por defecto.
Los adaptadores PDP externos y los ayudantes de paquetes de auditoría existen como utilidades exportadas. Aún no están completamente conectados a la ruta CLI por defecto.
{
"default_tier": "unknown",
"tools": {
"dangerous_tool": { "block": true },
"admin_tool": { "min_tier": "signed-known", "rate_limit": "5/hour" },
"read_tool": { "require": "any", "rate_limit": "100/hour" },
"*": { "rate_limit": "500/hour" }
},
"signing": {
"key_path": "./keys/gateway.json",
"issuer": "protect-mcp",
"enabled": true
},
"credentials": {
"internal_api": {
"inject": "env",
"name": "INTERNAL_API_KEY",
"value_env": "INTERNAL_API_KEY"
}
}
}Campo | Valores | Descripción |
|
| Bloquear explícitamente esta herramienta |
|
| Requisito de acceso básico |
|
| Nivel mínimo requerido si su host establece el estado de admisión |
|
| Límite de tasa (ej. |
Los nombres de las herramientas coinciden exactamente, con "*" como comodín de respaldo.
Añada a claude_desktop_config.json:
{
"mcpServers": {
"my-protected-server": {
"command": "npx",
"args": [
"-y", "protect-mcp",
"--policy", "/path/to/protect-mcp.json",
"--enforce",
"--", "node", "my-server.js"
]
}
}
}El mismo patrón: reemplace el comando del servidor con protect-mcp envolviéndolo.
protect-mcp [options] -- <command> [args...]
protect-mcp init
Commands:
init Generate Ed25519 keypair + config template
status Show decision stats and local passport identity
digest Generate a local human-readable summary
receipts Show recent persisted signed receipts
bundle Export an offline-verifiable audit bundle
Options:
--policy <path> Policy/config JSON file
--slug <slug> Service identifier for logs/receipts
--enforce Enable enforcement mode (default: shadow)
--verbose Enable debug logging
--help Show helpLa biblioteca también expone las primitivas que aún no están conectadas a la ruta CLI por defecto:
import {
ProtectGateway,
loadPolicy,
evaluateTier,
meetsMinTier,
resolveCredential,
initSigning,
signDecision,
queryExternalPDP,
buildDecisionContext,
createAuditBundle,
} from 'protect-mcp';Úselas si desea añadir:
admisión de manifiesto antes de que comience una sesión
un PDP externo (OPA, Cerbos o un webhook HTTP genérico)
integraciones personalizadas mediadas por credenciales
exportación de paquetes de auditoría alrededor de su propio almacén de recibos
Cada llamada a herramienta emite JSON estructurado a stderr:
[PROTECT_MCP] {"v":2,"tool":"read_file","decision":"allow","reason_code":"observe_mode","policy_digest":"none","mode":"shadow","timestamp":1710000000}Cuando la firma está configurada, sigue un recibo firmado:
[PROTECT_MCP_RECEIPT] {"v":2,"type":"decision_receipt","algorithm":"ed25519","kid":"...","issuer":"protect-mcp","issued_at":"2026-03-22T00:00:00Z","payload":{"tool":"read_file","decision":"allow","policy_digest":"...","mode":"shadow","request_id":"..."},"signature":"..."}Verifique con la CLI: npx @veritasacta/verify receipt.json
Verifique en el navegador: scopeblind.com/verify
El paquete exporta un ayudante para paquetes de auditoría autónomos:
{
"format": "scopeblind:audit-bundle",
"version": 1,
"tenant": "my-service",
"receipts": ["..."],
"verification": {
"algorithm": "ed25519",
"signing_keys": ["..."]
}
}Use createAuditBundle() alrededor de sus propios recibos firmados recopilados.
Primero sombra. Vea lo que hacen los agentes antes de aplicar nada.
Los recibos superan a los registros solo de panel. Los artefactos firmados deben ser verificables de forma independiente.
Mantenga las afirmaciones ajustadas. La ruta CLI por defecto aún no hace todo lo que la arquitectura a largo plazo soportará.
Capa sobre la autenticación existente. No desmonte su pila solo para añadir control y evidencia.
Se envían con protect-mcp: cada uno previene un ataque real:
Política | Incidente | Categorías OWASP |
| CVE-2025-6514: Secuestro de proxy OAuth MCP (437K entornos) | A01, A03 |
| Agente Terraform autónomo destruye producción | A05, A06 |
| Inyección de prompt mediante issue de GitHub manipulado | A01, A02, A03 |
| Robo de datos del agente mediante abuso de herramientas salientes | A02, A04 |
| Transacción financiera no autorizada | A05, A06 |
npx protect-mcp --policy node_modules/protect-mcp/policies/clinejection.json -- node server.jsAsignación completa de OWASP Agentic Top 10: scopeblind.com/docs/owasp
Soporta OPA, Cerbos, Cedar (AWS AgentCore) y puntos finales HTTP genéricos:
{
"policy_engine": "hybrid",
"external": {
"endpoint": "http://localhost:8181/v1/data/mcp/allow",
"format": "cedar",
"timeout_ms": 200,
"fallback": "deny"
}
}IETF Internet-Draft: draft-farley-acta-signed-receipts-00 — Recibos de decisión firmados para control de acceso máquina a máquina
Estado de la patente: 4 patentes provisionales australianas pendientes (2025-2026) que cubren recibos de decisión con divulgación configurable, puerta de enlace de llamada a herramientas, manifiestos de agente e identidad portátil
Verificación: Licencia MIT — npx @veritasacta/verify --self-test
MIT: libre de usar, modificar, distribuir y construir sobre él sin restricciones.
scopeblind.com · npm · GitHub · IETF Draft
Delete a file from the filesystem
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | File path to delete |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose that deletion is irreversible or mention behavior for missing paths or directories, which is critical for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short and front-loaded, but could be improved by including context about irreversibility without significant length increase.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a destructive operation with no output schema or annotations, the description lacks completeness: no mention of return values, errors, or required permissions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the parameter description 'File path to delete' is already clear; the description adds no extra meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'delete' and the resource 'file from the filesystem', distinguishing it from sibling tools like read_file (read) and write_file (write).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives, no context about prerequisites or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Deploy the application to production
| Name | Required | Description | Default |
|---|---|---|---|
| reason | No | Deployment reason | |
| environment | Yes | Target environment |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description fails to disclose behavioral traits like destructiveness, auth requirements, or failure modes.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely short (5 words), but underspecified – conciseness should not sacrifice necessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema; description does not explain return values, side effects, or deployment process outcomes.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so parameters are already well-documented. Description adds no extra meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description states 'deploy the application to production' – clear verb and resource, but slightly misleading as schema allows staging also. No confusion with sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives, no prerequisites or when-not-to-use mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read the contents of a file
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | File path to read |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only mentions reading without specifying encoding, size limits, existence requirements, or return format, leaving behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise single-sentence description that is front-loaded and efficient with no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite simplicity, description lacks details on return format, error handling, and behavioral constraints, which are critical for an agent invoking a file read tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a single parameter 'path' described as 'File path to read'; description adds no additional meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'read' and resource 'contents of a file', distinguishing it from sibling tools like write_file and delete_file.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives; usage is implied by the name and description but lacks context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the web for information
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description lacks details on behavior such as rate limits, result format, or limitations, leaving the agent uninformed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (one sentence) but fails to include necessary details, balancing brevity and completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and minimal annotations, the description does not adequately cover what the agent needs to know for successful use, such as result types or response details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one parameter 'query' with a schema description, and the tool description adds no additional meaning beyond what the schema already provides; high schema coverage baseline is 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Search the web for information' clearly states the verb and resource, and it distinguishes from siblings (file operations and deploy) which are unrelated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, and no exclusions or context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Write content to a file
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | File path to write | |
| content | Yes | Content to write |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose important behavioral traits such as whether the file is overwritten, permissions required, or error handling. Without annotations, the description carries the full burden, and it is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, to-the-point sentence with no wasted words. It earns its place by conveying the core action concisely.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple file write tool, the description lacks completeness. It does not mention return values, overwrite behavior, or any constraints, making it less useful for an AI agent to fully understand the tool's effect.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for both parameters, so the description adds no extra meaning. Baseline 3 is appropriate; the schema already documents path and content adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Write content to a file' clearly states the verb 'Write' and the resource 'content to a file', distinguishing it from sibling tools like read_file and delete_file. However, it does not specify whether it overwrites or appends, which would add more precision.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternatives. An explicit mention of use cases or exclusions (e.g., when to use deploy instead) is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
delete_filedeployread_fileweb_searchwrite_fileScored across 5 tools
Each tool targets a distinct action: file operations (delete, read, write), deployment, and web search. There is no overlap or ambiguity between them.
Most tools follow verb_noun pattern (delete_file, read_file, write_file, web_search), but 'deploy' lacks a noun, breaking the consistent pattern slightly.
5 tools is a reasonable count, but the mix of file management, deployment, and web search seems odd for a single server scope.
The tool set lacks obvious necessary operations for any single domain: e.g., no update for files, no environment or config for deployment, making it incomplete for a coherent purpose.
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
Security & DLP proxy for MCP: tool-poisoning scans, PII redaction on tool args/results. Beta.
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
Governed MCP gateway: one endpoint for your tools, with credential custody and audit log.
