Deploy
Deploy from your coding agent
You built an app with an AI coding tool and want your team to use it. Connect Brod to the tool once, ask it to deploy, and get back a private HTTPS address that only the people you choose can open.
claude mcp add --transport http brod https://brod.sh/mcpThe same three steps for every tool
These pages are for people who already have something working on their own machine. Each one covers the same three steps for a different tool.
Connect Brod
Add Brod to your coding tool as an MCP server.
Ask the agent to deploy
The agent deploys the app and gives you back its address.
Choose who can open it
Decide which people get access to the app.
What is the same whichever tool you use
- Private by default. A new app starts private to you and the workspace admins.
- A person confirms sharing. Opening an app to more people, or inviting someone, needs a person to confirm a link; the agent cannot do it alone.
- Data per app. Each app with server code gets its own database, key-value store and file storage.
- Versions and staging. Every deploy is a new version, and updates from an agent go to a staging address first.
- Rollback. Rolling back takes effect on the next request.
Keep reading
- MCP deploymentBrod is a remote MCP server for deploying apps. Connect Claude Code, Cursor, Codex or any MCP client over Streamable HTTP and let the agent deploy, read logs, set secrets and roll back.
- Internal toolsBrod runs the internal tools your team builds with Claude Code, Cursor or Codex: private address, team sign-in, roles, database, secrets, logs and rollback, deployed by your agent.
- SecurityHow Brod protects AI-generated internal apps: access checked before every request, private by default, human confirmation for sharing, encrypted secrets, per-app data, and what it does not protect against.
- GuidesPractical guides for people who built an app with an AI coding agent: add sign-in, secure it, share it with your team, and run it as a real internal tool.