Studio
Open-source control plane for your AI agents. Connect tools, hire agents, track every token and dollar
- Transport
- Not stated
- Package
- —
- Registry id
- —
No install snippet on purpose. A working MCP config is a command, its arguments and an environment block — the last two are where API keys live, so this catalogue never stores them and cannot publish them. Follow the link above for the authors' own instructions.
Studio is an open-source private AI workspace for organizations. Studio enables connecting private MCPs, configuring agents with team context, and provides SSO, permissions, audit logs, and cost control. Studio packages the infrastructure for internal AI adoption, including model routing, MCP authentication, agent configuration, SSO, RBAC, audit logs, and usage control.
Studio allows packaging context, tools, and policy into an agent, defining instructions, adding skills and files, granting approved MCP access, choosing a model policy, and publishing the agent for the organization. Studio tracks every model and tool call, breaking down usage by agent, connection, organization, or team member. Studio supports deployment on local, Docker, or Kubernetes infrastructure, using the user's own database, keys, and storage.
Studio is open-source and self-hosted, with no credit card required.
Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.