World Monitor
Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 102 tools.
Open-source MCP server: encrypted local keys and state, operator approval gates, a hash-chained log.
Elige la app de IA que usas y copia la configuración.
Pasó 2/3 revisiones · Funciona en tu computadora
Primero: ¿qué IA usas?
Elige tu app y los pasos aparecen abajo.
Funciona con Claude, pero hay que preparar algo antes
Instala Node.js en tu computadora primero (una sola vez) · Solo en la app de Claude para computadora (Windows o Mac), no en la web ni en el móvil
Una sola vez; sirve para todos los servidores que necesitan Node.js
SettingsDeveloperEdit Config
{
"mcpServers": {
"sanctuary": {
"command": "npx",
"args": [
"-y",
"@sanctuary-framework/mcp-server"
]
}
}
}Usa Sanctuary y dime qué puedes hacer por mí; luego muéstrame una cosa✓ Si Claude dice que está usando Sanctuary o muestra una herramienta de Sanctuary en la respuesta, ya está conectado
Nombres de menú comprobados con la ayuda de Anthropic el 11 nov 2026 · tu pantalla puede variar un poco según la versión
ChatGPT todavía no puede conectar Sanctuary
Sanctuary se instala en tu computadora, pero ChatGPT solo conecta servidores que funcionan en la web
A · Usa una app que pueda conectar Sanctuary
B · Otros en Otros que funcionan con ChatGPT
Elegidos entre los más usados de la misma categoría, solo los que se conectan con una dirección y sin clave
Funciona con Claude Code, pero hay que preparar algo antes
Instala Node.js en tu computadora primero (una sola vez)
Una sola vez; sirve para todos los servidores que necesitan Node.js
Mac: pulsa Command+Espacio y escribe Terminal · Windows: abre PowerShell
claude mcp add --scope user sanctuary -- npx -y @sanctuary-framework/mcp-serverDeberías ver Sanctuary en la lista como conectado
Usa Sanctuary y dime qué puedes hacer por mí; luego muéstrame una cosa✓ Si Claude Code dice que está usando Sanctuary o muestra una herramienta de Sanctuary en la respuesta, ya está conectado
Nombres de menú comprobados con la ayuda de Anthropic el 11 nov 2026 · tu pantalla puede variar un poco según la versión
Funciona con Cursor, pero hay que preparar algo antes
Instala Node.js en tu computadora primero (una sola vez)
Una sola vez; sirve para todos los servidores que necesitan Node.js
Usa Sanctuary y dime qué puedes hacer por mí; luego muéstrame una cosa✓ Si Cursor dice que está usando Sanctuary o muestra una herramienta de Sanctuary en la respuesta, ya está conectado
Nombres de menú comprobados con la ayuda de Cursor el 11 nov 2026 · tu pantalla puede variar un poco según la versión
Funciona con VS Code, pero hay que preparar algo antes
Instala Node.js en tu computadora primero (una sola vez)
Una sola vez; sirve para todos los servidores que necesitan Node.js
Usa Sanctuary y dime qué puedes hacer por mí; luego muéstrame una cosa✓ Si VS Code dice que está usando Sanctuary o muestra una herramienta de Sanctuary en la respuesta, ya está conectado
Nombres de menú comprobados con la ayuda de VS Code el 11 nov 2026 · tu pantalla puede variar un poco según la versión
Otras apps que usan MCP, como Windsurf, Zed o Gemini CLI, añaden servidores de forma distinta. Míralo en la lista de apps
Ver todas las apps que usan MCP →
La configuración JSON está en “Para desarrolladores”, abajo
Claude Code
claude mcp add --scope user sanctuary -- npx -y @sanctuary-framework/mcp-serverClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"sanctuary": {
"command": "npx",
"args": [
"-y",
"@sanctuary-framework/mcp-server"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"sanctuary": {
"command": "npx",
"args": [
"-y",
"@sanctuary-framework/mcp-server"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"sanctuary": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@sanctuary-framework/mcp-server"
]
}
}
}Esta configuración se genera a partir de la ficha del creador en el registro. Si el README dice otra cosa, sigue el README.
npm: @sanctuary-framework/mcp-serverSegún cómo se conecta este servidor y la documentación de cada app, comprobado el 10 nov 2026.
Se ejecutan en tu computadora en
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
Se ejecuta en tu computadora; la lista de herramientas aparece en tu app de IA después de instalarlo.
Revisamos información que cualquiera puede ver; no hemos leído el código. Las revisiones que no aplican no se cuentan. · Revisado el 12 nov 2026
Quien lo publicó (sanctuaryprotocol.ai) no es el dueño del repo (eriknewton); puede que otra persona lo haya listado
Último cambio de código: ayer
Usa Apache-2.0
Este se ejecuta en tu computadora; no hay endpoint en internet
Se ejecuta en tu computadora y usa ajustes locales en su lugar
Se ejecuta en tu computadora; solo podemos leer listas de herramientas de endpoints en internet
Pregunta, comparte un consejo o avisa de que no funciona. Ordenado por lo que la gente marcó como útil.
Aún no hay publicaciones. Sé la primera persona en preguntar o compartir.
Lo publicado aquí lo escriben usuarios, no el equipo de PopNx.
Aún no hay reseñas
Comparado con todos los servidores activos de esta categoría en el registro. Las estrellas solo cuentan cuando quien lo publica es dueño del repo.
Superó 2 de 3 revisiones básicas aplicables. No hemos leído el código. Antes de agregar una clave o un token, revisa qué acceso pide el servidor y usa una clave que tenga solo los permisos que necesitas.
El registro no indica ninguna clave obligatoria, aunque algunos servidores te piden iniciar sesión la primera vez que los usas.
Se ejecuta en tu computadora. Tu app de IA lo inicia cuando hace falta, y los datos no pasan por los servidores del creador (a menos que el propio servidor llame a un servicio en línea).
El repo de GitHub cambió por última vez ayer, y la última versión (1.8.4) llegó al registro hace 30 días.
Las apps compatibles con MCP, como Claude Desktop, Claude Code, Cursor y VS Code. También necesitas Node.js en tu computadora.
En la misma categoría: World Monitor, Claude Flow, Windmill
Servidores de la misma categoría hechos por otros creadores, ordenados por estrellas.
Cómo leer una tarjeta:↓ Descargas por semanai★ Estrellas de GitHubiTres pilares: reseñas · revisiones · usoiActualizado = fecha en que se publicó la última versión en el registroi
Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 102 tools.
AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Run Windmill scripts and flows and manage jobs, schedules, resources and variables.
Copiado tal cual del repo del creador. PopNx MCP no lo ha revisado ni lo respalda. Se quitaron HTML, imágenes y scripts. Los enlaces llevan fuera de este sitio.
Your agent will know you better than you know yourself. Make sure that data stays between you.
An AI agent running on your machine can do anything your account can do. It holds your credentials, reads your files, and talks to the whole internet, and a single poisoned web page can turn that into exfiltration. Every sandbox on offer today is one the agent, or its vendor, chooses to run inside. That is not a wall. That is a request.
Sanctuary is the wall under the agent, imposed by the operating system under a policy you sign, and it does not depend on the agent's cooperation. The keys never leave hardware you control. What the agent did is written to a hash-chained record you can read. No vendor, including us, sits in the path or can decrypt your state. It works with the harness you already run: Claude Code, Cursor, Hermes, OpenClaw, Cline, or Mastra (fixture-tested only; no live Mastra-agent drill is recorded), on your own machine today, any number of wrapped harnesses behind one persistent dashboard, with wrapping tested on representative harness paths and not proven for every harness version (Assurance Matrix, Agent wrapping, partial); another MCP-compatible harness can point its MCP config at Sanctuary, without a tested wrapping path; the fleet console and operator-cloud deployment are roadmapped (see Deployment modes).
npx -y @sanctuary-framework/mcp-server protect --claude-code
That one command puts the keys, audit trail, policy gates, and dashboard around the agent you already use. The operating-system wall is a separate privileged arming step on macOS through the signed app and extension path; see the Castle Wall macOS install and arm guide.
Quote the block below to your operator. It was written against v1.8.4, the npm latest release; main can be ahead of it, and every sentence traces to a line of this README or a row of the Assurance Matrix.
What Sanctuary is: the wall under the agent, imposed by the operating system under a policy you sign, and it does not depend on the agent's cooperation. The keys never leave hardware you control. What the agent did is written to a hash-chained record you can read.
What it is not: no Assurance Matrix row claims a filesystem or process sandbox for the agent; that is what your harness's own sandbox provides. The record is not an audited per-rule, per-flow trail. Windows enforcement is roadmapped; nothing enforces on Windows today. Linux enforcement is proven on Ubuntu 24.04 (x86-64) only; every other distribution or architecture remains unproven. Linux enforcement ships as the separate Castle Wall Linux 0.1.0-1 package (a GitHub pre-release), not in the npm package. Platforms and runtime: Node.js >= 22.0.0 and npm >= 10.0.0. macOS: proven. Linux: proven on Ubuntu 24.04 (x86-64) only, through the separate Castle Wall Linux 0.1.0-1 package (a GitHub pre-release, not part of the npm package). Windows: roadmapped. Install: npx -y @sanctuary-framework/mcp-server protect --claude-code --no-open --no-dashboard Verify: npx -y @sanctuary-framework/mcp-server doctor --json Uninstall: npx -y @sanctuary-framework/mcp-server uninstall Evidence: every capability claim traces to a row in ASSURANCE_MATRIX.md, and a row reads proven only when a captured drill on the platform that matters says so. Drill records are under docs/audit/.
Every capability claim in this repository traces to a row in the Assurance Matrix, and a row reads proven only when a captured drill on the platform that matters says so. A green test suite is not a claim. Read the matrix before you believe anything below.
| What you get | Status today |
|---|---|
| The wall. Outbound traffic from a wrapped agent is allowed or denied below the agent, per operator policy, per agent account | macOS: proven. A signed operator policy with a clean per-uid allow/deny demonstration that survives attended reboot cycles. Not an audited per-rule, per-flow trail. Linux: proven on Ubuntu 24.04 (x86-64) only. Linux enforcement ships as the separate Castle Wall Linux 0.1.0-1 package (a GitHub pre-release), not in the npm package. On Ubuntu 24.04 (x86-64), a fresh install of that package enforces a signed operator policy per user account: blocked destinations stay blocked and allowed ones connect, through five reboots, on three fresh servers, with the evidence checked by two independent reviewers. Fault-injection witnesses, a real-agent harness, and every other distribution or architecture remain unproven. Windows: roadmapped. |
| Custody. Keys and state under your passphrase, on your hardware | Proven. Ed25519 identity, Argon2id unlock, per-purpose derived subkeys, encrypted state at rest. The passphrase lives in the macOS Keychain or Linux Secret Service and generation fails closed without it. |
| The gate. Policy you set, frozen at startup, the agent cannot read or infer; three approval tiers with a human on the irreversible ones | Proven. Cooperative gates on every MCP call Sanctuary executes or forwards. The wall is what makes the gate more than a request. |
| The record. Append-only, hash-chained audit of what the agent did | Partial. The chain is live; production call sites sign checkpoints when the fortress holds an identity. Fortresses with no identity and the root daemon split audit store write honest unsigned checkpoints. The row stays partial pending the IC-05 external-verifier drill and the remaining local tamper-evidence follow-up. |
| Exit. Keys, state, memory and reputation leave with you | Partial. Export and import ship; three exit-bundle gaps are open (IC-07, IC-08, IC-09). |
Plenty of tools can sandbox an agent when the agent, or its harness, chooses to run inside one. Sanctuary is built for the harder promise: the wall is imposed by the operator, and does not depend on the agent's cooperation. The problem underneath is ambient authority, the fact that code can act with every permission its process has. Language-level answers (capabilities, information-flow typing, functional runtimes) are real and we welcome them, and every one of them still needs something outside the interpreter that holds the credentials, checks the policy and decides what actually leaves the machine. Sanctuary is that something, for whatever runtime you choose. It composes with Concordia (agent negotiation) and Verascore (portable reputation), each in its own repo and neither required.
Why this exists: The Base Layer.
Your harness already has a sandbox, and the two are built for different questions. The harness sandbox bounds what the agent's shell commands can touch; Sanctuary bounds where the agent account's traffic can go and holds the keys and the record, whether or not the agent cooperates. The middle column states only what each vendor's own page says; the first column states only what an Assurance Matrix row proves.
| Where you run | What Sanctuary adds (matrix row) | What the harness sandbox gives that Sanctuary never claims | Run both? |
|---|---|---|---|
| macOS, wall armed | OS-level egress enforcement below the agent: a signed operator policy with a clean per-uid allow/deny demonstration that survives attended reboot cycles ("Egress enforcement: macOS", proven; one host and one OS version; not an audited per-rule, per-flow trail). Plus custody ("State encryption", proven), approval gates ("Approval gating", proven), and the hash-chained record ("Tamper-evident audit chain", partial) | Filesystem write limits and process-tree limits on the shell commands the harness runs; a network allowlist the harness itself enforces | Yes. The sandbox is chosen by the harness and can be retried outside of; the wall is imposed by the operator below the agent |
| macOS, wall not armed | Custody, approval gates, and the record, as above; no egress enforcement | As above | Yes. Without the wall, egress is bounded only by the harness sandbox's own domain list |
| Ubuntu 24.04 (x86-64) | Kernel egress enforcement per user account on a fresh install of the separate Castle Wall Linux 0.1.0-1 package (a GitHub pre-release, not part of the npm package) ("Egress enforcement: Linux", proven for exactly the claim in the table above and nothing wider). Plus custody, gates, and the record; generated custody needs an unlocked Secret Service | As above | Yes |
| Other Linux distributions or architectures | Custody, gates, and the record; egress enforcement unproven (the matrix row is Ubuntu 24.04 x86-64 only) | As above | Yes, and treat the wall as absent |
| Windows | Read-only custody may open an already-enveloped fortress; custody mutation and install readiness fail closed; enforcement roadmapped | Claude Code: unsandboxed on native Windows, sandboxed under WSL2. Codex: a native Windows sandbox in PowerShell and the Linux sandbox under WSL2. Cursor: no Windows sandbox is described | Nothing to arm on the Sanctuary side yet |
Harness column sources, each fetched 2026-10-12 (none of the three pages shows a last-updated date; the Cursor page's newest changelog entry is dated 2026-10-01):
bubblewrap plus socat on Linux and WSL2; network goes through a local proxy checked against an allowed-domain list; on native Windows commands run unsandboxed; MCP servers, hooks, and the built-in file and web tools run outside it; Claude can ask to retry a failed command unsandboxed.bubblewrap on Linux and WSL2, a native Windows sandbox in PowerShell; workspace-write is the default mode and danger-full-access removes the filesystem and network boundaries.sandbox.json; Seatbelt through sandbox-exec on macOS, Landlock plus seccomp on Linux kernel 6.2 or later with a Bubblewrap fallback; no Windows sandbox is described; a command that fails on a sandbox restriction can be rerun outside it after classifier review.The argument for why the two layers are different problems: Containment is an isolation problem.
In this order, about an hour:
proven only on a captured drill; a green suite is not a claim.