Appearance

Updating visuals

If you see any images containing outdated UI, please bear with us.

We are updating all content as quickly as possible to mirror our new UI.

WeWeb MCP ​

Use the WeWeb MCP server to let an external AI agent work on your WeWeb projects. Instead of building inside the editor with WeWeb AI, you can stay in the AI client you already use, such as ChatGPT, Claude, Cursor, Codex, or Antigravity, and ask it to create pages, manage your backend, edit workflows, and inspect your project through natural language.

The server is available at:

https://ai-api.weweb.io/v1/mcp

WARNING

Tool calls run against your real project and can create, edit, or delete resources. We recommend reviewing changes as the agent works.

MCP trial ​

For new Workspaces, the WeWeb MCP server is available on a 14-day free trial. The trial starts when your AI client calls a WeWeb tool for the first time. For continued access, you must purchase or upgrade your existing workspace plan to Pro or Partner.

If you have a Partner plan and are working in your customer's workspace, your customer must have at least a Pro plan for you to access their projects using the MCP server.

Learn more about WeWeb pricing →

WeWeb recommends Claude Opus ​

For the best results today, we recommend using Claude Opus as the underlying model. In our testing, it follows WeWeb tooling more reliably and produces higher-quality output than other models. As the MCP server matures, we'll broaden the list of recommended models.

What is MCP? ​

The Model Context Protocol (MCP) is an open standard that lets AI agents discover and call external tools in a consistent way. By exposing WeWeb as an MCP server, any compatible client can list the available WeWeb tools and invoke them to act on your project.

This is the inverse of a chat connector: rather than WeWeb calling out to an external service, an external agent calls into WeWeb to do the work for you.

How it works ​

  1. Connect your AI client to the WeWeb MCP server. See the setup steps for your client →
  2. Authenticate. On first use, the client opens a browser window so you can sign in to WeWeb and authorize access.
  3. Tell the agent which project to work on. Ask it to list your workspaces and projects, then name the one you want. The agent targets that project on every call, so there is no persistent "active project" to switch.
  4. Build and iterate. Describe what you want and let the agent call the relevant WeWeb tools.

What your agent can do ​

Once connected, the agent works with the same building blocks you use in the editor: pages and elements, your design system, variables and formulas, frontend and backend workflows, tables and table views, authentication and users, integrations, and coded components.

See all available tools →

Plugin actions ​

The MCP does not expose plugin actions, so your agent cannot build with a plugin such as Xano or Supabase. When your provider has an Integration, switching to it lets the agent work normally, because integration actions are available through MCP.

Learn more about plugin actions and MCP →

CONTINUE LEARNING

Ready to connect? Each client has its own way of adding an MCP server, whether that is a custom connector, a config file, or a single terminal command.

Install WeWeb MCP in your client →