Bietet KI-Clients einen zentral gesteuerten MCP-Endpoint für Agents, Tools, Modelle und die Kostenverfolgung pro Aufruf.
Auch bekannt als decocms/studio, deco-cli, decocms
- Stars
- 418
- Tools
- —
- Downloads, 30 Tage
- 85.291
- Neueste Version
- —
- Letzter Commit
- 14. Nov. 2026
- Lizenz
- MIT
Was ist deco Studio MCP?
deco Studio ist ein MCP server. Bietet KI-Clients einen zentral gesteuerten MCP-Endpoint für Agents, Tools, Modelle und die Kostenverfolgung pro Aufruf.
Zusammenfassung generiert aus dem README des Projekts
Über deco Studio MCP server
Studio bietet eine zentrale Control Plane für den unternehmensweiten Einsatz von KI. Es fungiert als ein einziger, gesteuerter MCP-Endpoint, der Agents, Tools und Modelle verwaltet und gleichzeitig die Kosten pro Aufruf trackt. Unternehmen können es nutzen, um Kontext und Policies in publishbare Agents zu verpacken, die von Clients wie Cursor, Claude Desktop oder VS Code aufgerufen werden können.
User können private Systeme wie GitHub, Slack oder Postgres über einen verschlüsselten Vault anbinden. So können Teams MCP-Capabilities teilen, ohne die eigentlichen Credentials weitergeben zu müssen. Die Plattform unterstützt austauschbare Modell-Layer und ermöglicht Verbindungen zu OpenRouter oder direkten Providern wie Anthropic, OpenAI und Google. Es kann lokal mittels Docker Compose mit PostgreSQL und NATS bereitgestellt oder über einen Cloud-Service für den Zugriff durch Remote-Teams genutzt werden.
Administratoren behalten durch Observability-Dashboards den Überblick, die Latenz, Fehler und Tokens tracken. Das System bietet Management-Features auf Enterprise-Niveau, einschließlich SSO, rollenbasierter Zugriffskontrolle und Audit Logs, um eine sichere und nachvollziehbare KI-Nutzung im gesamten Unternehmen zu gewährleisten.
Was du damit machen kannst
- 1Interne Tools sicher teilenEin Developer kann einem Agent Zugriff auf eine private Datenbank gewähren, ohne die zugrunde liegenden Credentials offenzulegen.
- 2KI-Betriebskosten überwachenEin Administrator kann genau nachverfolgen, wie viel Geld für verschiedene Modelle und Agents ausgegeben wird.
- 3Agent-Konfigurationen standardisierenTeams können spezifische Agents mit vordefinierten Instruktionen und Tools erstellen, die von der gesamten Organisation genutzt werden können.
- 4Multi-Model-Routing verwaltenEin Engineer kann über eine einzige Schnittstelle zwischen verschiedenen KI-Providern für unterschiedliche Aufgaben wechseln.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du deco Studio MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügendeco Studio MCP in Claude Code installieren
$ claude mcp add studio -- npx -y deco-clideco Studio MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"studio": {
"command": "npx",
"args": [
"-y",
"deco-cli"
]
}
}
}deco Studio MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"studio": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"deco-cli"
]
}
}
}deco Studio MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"studio","type":"stdio","command":"npx","args":["-y","deco-cli"]}'deco Studio MCP in Claude Desktop installieren
claude_desktop_config.json
{
"mcpServers": {
"studio": {
"command": "npx",
"args": [
"-y",
"deco-cli"
]
}
}
}deco Studio MCP in Codex installieren
$ codex mcp add studio -- npx -y deco-clideco Studio MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.studio] command = "npx" args = ["-y", "deco-cli"]
deco Studio MCP in Gemini CLI installieren
$ gemini mcp add -s user studio npx -- -y deco-clideco Studio MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"studio": {
"command": "npx",
"args": [
"-y",
"deco-cli"
]
}
}
}Automatisierte Checks
Geluften am 12. Nov. 2026Vollständiger Bericht →Unsere automatisierten Checks bestanden. Das ist kein Security-Audit: Lies den Code und gib dem Server nur den minimal notwendigen Zugriff. Wie die Checks funktionieren
- Source Repository verknüpft und erreichbarBestanden
- Open Source Lizenz (OSI)Bestanden
- Commit oder Release im letzten JahrBestanden
- Package-Name ähnelt keinem populären PackageBestanden
- Remote Endpoint nutzt HTTPSNicht geprüft
- Destruktive Tools sind markiertNicht geprüft
- Keine versteckten Anweisungen an das ModellBestanden
- Keine kritischen Advisories im Paket oder seinen AbhängigkeitenNicht geprüft
README
Auf GitHub ansehenTL;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
deco Studio MCP Fragen
Wie füge ich deco Studio MCP zu Claude Code hinzu?
Führe claude mcp add studio -- npx -y deco-cli in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich deco Studio MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Wie starte ich deco Studio lokal?
Klone das Repository und starte es mit Docker Compose, öffne dann localhost:4000. Compose setzt PostgreSQL, NATS, Object Storage, Migrations sowie die API und die Web-App auf.
Wie speichert Studio die Credentials für verbundene Tools?
MCP server Tokens werden in einem verschlüsselten Vault auf Organisationsebene gespeichert. Der Zugriff wird pro Organisation, Rolle oder Agent gewährt.
Kann ich verschiedene KI-Modell-Provider nutzen?
Ja, Studio routet Modelle über OpenRouter oder direkte Provider wie Anthropic, OpenAI und Google, die pro Agent und Tool ausgewählt werden können.
Was kann ich über die Nutzung der Agents tracken?
Jeder Modell- und Tool-Aufruf wird mit User, Agent, Modell, Latenz, Fehlern, Tokens und Kosten protokolliert, aufgeschlüsselt nach Agent, Verbindung, Organisation oder Teammitglied.
Unterstützt Studio SSO und rollenbasierte Zugriffskontrolle?
Ja, es bietet SSO und RBAC via Better Auth mit OAuth 2.1 und tool-spezifischen API-Keys sowie Organisations-Isolation und Audit Logs für Self-hosted-Deployments.