Proporciona a los clientes de IA un único endpoint MCP gobernado para agentes, herramientas, modelos y seguimiento de costes por llamada.
También conocido como decocms/studio, deco-cli, decocms
- Stars
- 418
- Herramientas
- —
- Descargas, 30 días
- 85.291
- Última versión
- —
- Último commit
- 14 nov 2026
- Licencia
- MIT
¿Qué es deco Studio MCP?
deco Studio es un MCP server. Proporciona a los clientes de IA un único endpoint MCP gobernado para agentes, herramientas, modelos y seguimiento de costes por llamada.
Resumen generado a partir del README del proyecto
Acerca del MCP server de deco Studio
Studio proporciona un plano de control centralizado para el despliegue de IA en organizaciones. Actúa como un único endpoint MCP gobernado que gestiona agentes, herramientas y modelos, al tiempo que realiza un seguimiento de los costes por llamada. Las organizaciones pueden utilizarlo para empaquetar contexto y políticas en agentes publicables que pueden llamarse desde clientes como Cursor, Claude Desktop o VS Code.
Los usuarios pueden conectar sistemas privados como GitHub, Slack o Postgres a través de una bóveda cifrada, lo que permite a los equipos compartir capacidades de MCP sin compartir las credenciales reales. La plataforma admite capas de modelos intercambiables, permitiendo conexiones con OpenRouter o proveedores directos como Anthropic, OpenAI y Google. Puede desplegarse localmente usando Docker Compose con PostgreSQL y NATS, o utilizarse mediante un servicio en la nube para el acceso de equipos remotos.
Los administradores mantienen la supervisión mediante paneles de observabilidad que rastrean la latencia, los errores y los tokens. El sistema ofrece funciones de gestión de nivel empresarial, incluyendo SSO, control de acceso basado en roles y registros de auditoría para garantizar un uso de la IA seguro y responsable en toda la empresa.
Qué puedes hacer con él
- 1Compartir herramientas internas de forma seguraUn desarrollador puede conceder acceso a un agente a una base de datos privada sin exponer las credenciales subyacentes.
- 2Monitorizar los costes operativos de la IAUn administrador puede rastrear exactamente cuánto dinero se está gastando en diferentes modelos y agentes.
- 3Estandarizar las configuraciones de los agentesLos equipos pueden crear agentes específicos con instrucciones y herramientas predefinidas para ser utilizados por toda la organización.
- 4Gestionar el enrutamiento multi-modeloUn ingeniero puede cambiar entre diferentes proveedores de IA para distintas tareas a través de una única interfaz.
Escrito a partir del README del proyecto. Cada caso de uso se verifica con una cita del mismo.
Cómo instalar deco Studio MCP
Formatos verificados el 10 nov 2026Añadir a CursorAñadir a GooseInstalar deco Studio MCP en Claude Code
$ claude mcp add studio -- npx -y deco-cliInstalar deco Studio MCP en Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"studio": {
"command": "npx",
"args": [
"-y",
"deco-cli"
]
}
}
}Instalar deco Studio MCP en VS Code
.vscode/mcp.json
{
"servers": {
"studio": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"deco-cli"
]
}
}
}Instalar deco Studio MCP en VS Code CLI
$ code --add-mcp '{"name":"studio","type":"stdio","command":"npx","args":["-y","deco-cli"]}'Instalar deco Studio MCP en Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"studio": {
"command": "npx",
"args": [
"-y",
"deco-cli"
]
}
}
}Instalar deco Studio MCP en Codex
$ codex mcp add studio -- npx -y deco-cliInstalar deco Studio MCP en Codex config.toml
~/.codex/config.toml
[mcp_servers.studio] command = "npx" args = ["-y", "deco-cli"]
Instalar deco Studio MCP en Gemini CLI
$ gemini mcp add -s user studio npx -- -y deco-cliInstalar deco Studio MCP en Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"studio": {
"command": "npx",
"args": [
"-y",
"deco-cli"
]
}
}
}Verificaciones automáticas
Ejecutado 12 nov 2026Informe completo →Pasó nuestras verificaciones automáticas. Esto no es una auditoría de seguridad: lee el código y dale al servidor el acceso más limitado que necesite. Cómo funcionan las verificaciones
- Repositorio de origen vinculado y accesibleAprobado
- Licencia de código abierto (OSI)Aprobado
- Commit o lanzamiento en el último añoAprobado
- El nombre del paquete no es similar a un paquete popularAprobado
- El endpoint remoto usa HTTPSNo verificado
- Las herramientas destructivas están etiquetadasNo verificado
- Sin instrucciones ocultas para el modeloAprobado
- No hay avisos críticos en el paquete ni en sus dependenciasNo verificado
README
Ver en GitHubTL;DR: Your team needs a secure internal vibecoding platform. You just found it. Configure agents with team context. Connect private MCPs once — share capabilities, not credentials. Keep the model layer interchangeable. Roll out across the organization with SSO, RBAC, audit logs, and cost controls — all through one MCP endpoint. Local-first. Self-host or use the cloud.
What is deco Studio?
Studio packages the infrastructure behind an internal AI rollout: model routing, MCP authentication, agent configuration, SSO, RBAC, audit logs, and usage accounting. Your teams get chat. You keep control.
Under the hood it's one control plane for your AI agents — one MCP endpoint for all your agents, tools, and models. Agents package context, tools, and policy into something you publish to the organization. Connections give them governed access to your systems — GitHub, Slack, Postgres, Sentry, anything that speaks MCP — with tokens stored in an encrypted vault. Models stay interchangeable: OpenRouter or direct providers, chosen per agent and per tool.
Start with one team. Standardize approved models, tools, and context. Expand across the organization without copying secrets or rebuilding the platform. Install locally and it stays private; sync to the cloud for remote access, team roles, and shared billing.
┌─────────────────────────────────────────────────────────────────┐
│ Clients │
│ Cursor · Claude · VS Code · Custom Agents │
└───────────────────────────┬─────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────┐
│ DECO STUDIO │
│ Agents · Connections · Models · Vault · Observability │
└───────────────────────────┬─────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────┐
│ Tools & MCP Servers │
│ GitHub · Slack · Postgres · OpenRouter · Your APIs │
└─────────────────────────────────────────────────────────────────┘
Quick Start
Install Docker with Compose, then run from source:
git clone https://github.com/decocms/studio.git
cd studio
docker compose up --build --watch
Open http://localhost:4000. Compose starts PostgreSQL, NATS, object storage, migrations, and the hot-reloading API and web app. See CONTRIBUTING.md for contributor setup and worktrees.
What you get
Agents
Package context, tools, and policy into an agent. Define instructions, add skills and files, grant approved MCP access, choose a model policy, then publish the agent to the organization. Each agent is its own MCP endpoint — callable from Cursor, Claude Desktop, your own code, or another agent. Agents compose, and every action is tracked with cost attribution.
Connections
Connect private systems once, securely. Register MCP servers at the organization level through a web UI with one-click OAuth — no JSON configs. Tokens live in the encrypted vault, and you grant tool-level access by organization, role, or agent. Share MCP capabilities — not credentials.
As tool surfaces grow, Studio exposes Virtual MCPs — one endpoint, different strategies for which tools to surface:
- Full-context: expose everything (simple, deterministic, good for small toolsets)
- Smart selection: narrow the toolset before execution
- Code execution: load tools on demand in a sandbox
Models
Keep the AI layer interchangeable. Use OpenRouter or connect Anthropic, OpenAI, Google, or any compatible provider directly — the best model for each agent and tool, behind one router. For coding work, engineers can link their own Claude Code or Codex session and use the subscription already authenticated on their machine.
Projects
Projects bring agents and connections together around a goal. The project's UI adapts to what's inside — add a content agent and a CMS connection, the sidebar shows content management; add an analytics agent and a database, it shows dashboards and queries. The UI you see is the UI that's relevant for operating that project.
Observability
Account for every model and tool call. Trace the user, agent, model, tools, latency, errors, tokens, and cost for every thread. Break usage down by agent, connection, organization, or teammate — one dashboard.
From your desktop to your org
| Local | Docker Compose on your laptop, including PostgreSQL, NATS, and object storage. |
| Cloud | Log in to studio.decocms.com. Control local projects from any browser. |
| Team | Invite people. SSO and role-based access. Shared connections. Cost attribution. |
| Enterprise | Self-hosted. Organization isolation, tool-scoped API keys, audit logs. Your infra, your rules. |
Core Capabilities
| Capability | What it does |
|---|---|
| Agents | Package context, tools, and policy into publishable agents with cost attribution |
| Connections | Route MCP traffic through one governed endpoint with auth, proxy, and encrypted token vault |
| Models | Interchangeable AI layer — OpenRouter or direct providers, model policy per agent |
| Projects | Organize agents and connections around goals with an adaptive UI |
| Virtual MCPs | Compose and expose governed toolsets as new MCP endpoints |
| Observability | Traces, costs, errors, and latency per user, agent, and connection — one dashboard |
| Access Control | SSO + RBAC via Better Auth — OAuth 2.1 and tool-scoped API keys per workspace/project |
| Multi-tenancy | Organization/project isolation for config, credentials, policies, and audit logs |
| Bindings | Capability contracts so tools target interfaces, not specific implementations |
| Store | Discover and install agents, tools, and templates |
Define Tools
Type-safe, audited, observable, callable via MCP.
import { z } from "zod";
import { defineTool } from "~/core/define-tool";
export const CONNECTION_CREATE = defineTool({
name: "CONNECTION_CREATE",
description: "Create a new MCP connection",
inputSchema: z.object({
name: z.string(),
connection: z.object({
type: z.enum(["HTTP", "SSE", "WebSocket"]),
url: z.string().url(),
token: z.string().optional(),
}),
}),
outputSchema: z.object({
id: z.string(),
scope: z.enum(["workspace", "project"]),
}),
handler: async (input, ctx) => {
await ctx.access.check();
const conn = await ctx.storage.connections.create({
projectId: ctx.project?.id ?? null,
...input,
createdById: ctx.auth.user!.id,
});
return { id: conn.id, scope: conn.projectId ? "project" : "workspace" };
},
});
Every tool call gets input/output validation, access control, audit logging, and OpenTelemetry traces automatically.
Documentation
Studio documentation lives in docs-tanstack, alongside the Storefront documentation. Update public product guides and architecture there. Workspace READMEs and engineering plans stay here with the implementation.
Project Structure
Applications
| Workspace | Purpose |
|---|---|
apps/api |
Hono API, authentication, tools, storage, migrations, and the deco CLI |
apps/web |
Vite and React 19 administration interface |
Packages
| Workspace | Purpose |
|---|---|
packages/bindings |
Runtime-validated MCP capability contracts |
packages/create-deco |
npm create deco project scaffolding CLI |
packages/e2e |
Black-box Playwright suite for Studio |
packages/harness-runner |
In-sandbox coding-agent harness process |
packages/mcp-utils |
MCP proxy, gateway, aggregation, and sandbox primitives |
packages/runtime |
Runtime helpers for MCP servers, OAuth, tools, and triggers |
packages/sandbox |
Agent sandbox lifecycle, daemon, dispatch, and proxy implementation |
packages/sandbox-controller |
Sandbox provider bundled for a remote host such as the control plane |
packages/shared |
Private isomorphic contracts, SDK utilities, and async primitives |
packages/typegen |
Typed client generator for Studio Virtual MCPs |
packages/ui |
Internal React design system |
Development
bun install # Install dependencies
bun run dev # Docker Compose Watch: dependencies, migrations, API + web
bun test # Run tests
bun run check # Type check
bun run lint # Lint
bun run fmt # Format
App-specific commands
bun run --cwd=apps/web dev # Vite dev server (port 4000)
bun run --cwd=apps/api dev:server # Hono server with hot reload
bun run --cwd=apps/api migrate # Run database migrations
For parallel worktrees, Compose lifecycle commands, and frontend-only work, see CONTRIBUTING.md.
Deploy Anywhere
# Docker Compose: released Studio + PostgreSQL + NATS + object storage
docker compose -f selfhost/examples/docker-compose/compose.yaml up -d
# Kubernetes (Helm)
helm install deco-studio oci://ghcr.io/decocms/chart-deco-studio --version <version> -n deco-studio --create-namespace
Run Studio with Docker Compose or Kubernetes on your own infrastructure.
What you need to run it
| Tier | Footprint |
|---|---|
| Laptop | Docker with Compose; the development stack includes its dependencies. |
| Docker | Published Studio image with configured PostgreSQL, NATS, and object storage. |
| Production (Helm) | PostgreSQL you bring, plus NATS for streaming and cross-pod coordination, ClickHouse + OTel Collector (traces and analytics), and the sandbox operator (isolated agent environments on Kubernetes). Your identity provider, your model keys, your storage. |
Production topology
graph TB
clients["MCP clients — Cursor · Claude · VS Code · your code"]
clients -->|"one MCP endpoint · SSO · RBAC · audit"| api
subgraph k8s ["Kubernetes (Helm)"]
api["Studio API + Admin UI"]
api --> sandbox["Agent sandboxes<br/>(sandbox-operator)"]
api <-->|"streams and broadcasts"| nats["NATS"]
api -->|"traces · costs"| otel["OTel Collector"]
nats <-->|"streams and broadcasts"| worker["Workers<br/>DBOS runs"]
otel --> ch[("ClickHouse")]
end
pg[("PostgreSQL")]
api --> pg
worker <-->|"DBOS queues and journal"| pg
subgraph upstream ["Models & tools"]
models["Anthropic · OpenAI<br/>OpenRouter · Ollama"]
mcps["GitHub · Slack · Postgres<br/>your MCP servers"]
end
api -->|"model routing · vaulted credentials"| upstream
Every box is optional except Studio and PostgreSQL — start small, turn on the rest as the rollout grows.
Tech Stack
| Layer | Tech |
|---|---|
| Runtime | Bun / Node |
| Language | TypeScript + Zod |
| Framework | Hono (API) + Vite + React 19 |
| Database | Kysely → PostgreSQL |
| Auth | Better Auth (OAuth 2.1 + API keys) |
| Observability | OpenTelemetry |
| UI | React 19 + Tailwind v4 + shadcn |
| Protocol | Model Context Protocol (MCP) |
Roadmap
- Agent marketplace — discover, hire, and compose agents
- Declarative planning engine
- Cost analytics and spend caps
- Remote access from any browser
- Live tracing debugger
- Workflow orchestration with guardrails
License
MIT — see LICENSE.md.
Questions? builders@decocms.com
Contributing
bun run fmt # Format
bun run lint # Lint
bun test # Test
See AGENTS.md for coding guidelines, CONTRIBUTING.md for the contribution workflow, and TESTING.md for the testing rules.
Good first steps: open an issue, pick one labeled good first issue, or ask in Discord.
Contributors
Studio is built in the open. Thanks to everyone who has shipped a commit.
Maintainers — see MAINTAINERS.txt:
@guitavano · @viktormarinho · @mcandeia · @pedrofrxncx · @JonasJesus42 · @aka-sacci-ccr · @vibegui · @tlgimenes · @vibe-dex · @nicacioliveira
Preguntas sobre deco Studio MCP
¿Cómo agrego deco Studio MCP a Claude Code?
Ejecuta claude mcp add studio -- npx -y deco-cli en tu terminal. Añade --scope user para que esté disponible en todos los proyectos.
¿Cómo agrego deco Studio MCP a Cursor?
Abre ~/.cursor/mcp.json y añade el servidor en mcpServers, usando la configuración de Cursor que se muestra en la sección de instalación de arriba.
¿Cómo ejecuto deco Studio localmente?
Clona el repositorio e inícialo con Docker Compose, luego abre localhost:4000. Compose levanta PostgreSQL, NATS, almacenamiento de objetos, migraciones, la API y la aplicación web.
¿Cómo almacena Studio las credenciales de las herramientas conectadas?
Los tokens del MCP server se guardan en una bóveda cifrada a nivel de organización, y el acceso se concede por organización, rol o agente.
¿Puedo usar diferentes proveedores de modelos de IA?
Sí, Studio enruta los modelos a través de OpenRouter o proveedores directos como Anthropic, OpenAI y Google, elegidos por agente y herramienta.
¿Qué puedo rastrear sobre el uso de los agentes?
Cada llamada a modelos y herramientas se rastrea con usuario, agente, modelo, latencia, errores, tokens y coste, desglosado por agente, conexión, organización o compañero de equipo.
¿Soporta Studio SSO y acceso basado en roles?
Sí, ofrece SSO y RBAC mediante Better Auth con OAuth 2.1 y claves API con alcance limitado a herramientas, además de aislamiento de organización y registros de auditoría para despliegues self-hosted.