WeWeb MCP

WeWeb MCP connects Claude Code, Cursor, Codex, Antigravity, ChatGPT, and other AI agents to WeWeb projects, turning briefs and app logic into editable applications.

AI Agent Development

AI App Builder

No-Code & Low-Code

Visit Website

AI-assisted development inside WeWeb

WeWeb MCP is an MCP server for building inside WeWeb with an external AI agent. It connects named clients including Claude Code, Cursor, Codex, Antigravity, and ChatGPT, while also supporting other MCP-compatible agents. The agent can work from briefs, designs, and application logic to make changes to a WeWeb project.

The workflow is designed to combine agent-assisted development with WeWeb's visual editor. Users configure the MCP server in their client, sign in to authorize access, select a workspace and project, and describe the work they want done. Agent changes can then be reviewed in WeWeb, refined through further prompts, or edited manually. The service uses the connected agent's account, model, and tokens rather than WeWeb AI credits.

Core capabilities

Connect an AI coding agent

Connect Claude Code, Cursor, Codex, Antigravity, ChatGPT, or another MCP-compatible agent through an MCP client configuration.

Build from briefs and app logic

Use the connected agent to turn briefs, designs, product requirements, and app logic into pages, forms, states, workflows, and other WeWeb project changes.

Scope agent access

Choose whether the agent works across the full project or focuses on a specific page, workflow, data area, or design-system task.

Review and edit visually

Review agent output in WeWeb and continue prompting or make changes directly in the visual editor instead of treating generated work as final.

Apply design-system context

Bring design rules from sources such as Figma, Google Stitch, Claude Design, or design.md, then create reusable components with no-code properties using shadcn, React references, or custom coded components.

Connect project context

Work across an MCP stack by pairing WeWeb with backend MCP services such as Xano, Supabase, or Airtable, as well as APIs and product context from documents, websites, Figma files, and media assets.

Practical use cases

Turn a PRD into an app foundation
Give an agent a product brief or PRD and have it structure the initial application around user journeys, pages, forms, states, and flows, then refine the result in WeWeb.
Build from a design system
Provide brand rules from Figma, Google Stitch, Claude Design, or design.md so the agent can build reusable components and a more consistent interface instead of relying on default styling.
Build a data-connected frontend
Pair WeWeb with backend MCP services such as Xano, Supabase, or Airtable to create a frontend in the context of data, fields, relationships, authentication, storage, and backend workflows.
Refactor an existing project
Use an agent to identify unused variables, outdated workflows, test components, naming inconsistencies, and leftover build artifacts while keeping the project available for visual inspection.
Make controlled project changes
Limit an agent to a defined page, workflow, data area, or design-system task when a team wants targeted changes rather than broad project access.

Pros and Cons

Pros

Supports several named AI clients and any MCP-compatible agent.
Lets users limit work to a full project or a narrower page, workflow, data, or design-system scope.
Generated changes remain inspectable and editable in the WeWeb visual editor.
Can be combined with backend MCP services and external project context.
Uses the connected agent's tokens instead of WeWeb AI credits.

Cons

The workflow requires an MCP-compatible client, server configuration, and WeWeb authorization before the agent can work on a project.
The source does not specify detailed tool permissions, usage limits, generated-output guarantees, or behavior for every MCP-compatible agent.

FAQ

What is WeWeb MCP?

WeWeb MCP is a Model Context Protocol server that connects compatible AI agents to WeWeb so they can help build and modify WeWeb projects. Changes remain reviewable in the WeWeb visual editor.

Which AI agents can connect to WeWeb MCP?

The page names Claude Code, Cursor, Codex, Antigravity, and ChatGPT, and says the service works with any MCP-compatible agent. The agent uses its own account, model, and tokens.

Does WeWeb MCP use WeWeb AI credits?

The product page says WeWeb MCP runs on the connected agent's tokens rather than WeWeb AI credits. The pricing page lists a 14-day WeWeb MCP Server trial on the Free plan and unlimited MCP Server access on the Pro plan; other plan behavior is not specified in the source.

Can I control what the agent can access?

Yes. You can give the agent access to the full project or focus it on a particular page, workflow, data area, or design-system task. The agent must be authorized after you sign in to WeWeb.

Do projects and MCP workflows remain editable in WeWeb?

Yes. You can inspect the generated result in WeWeb, continue prompting the agent, or edit the project yourself in the visual editor. The page also describes working with other MCP servers, including backend MCP services such as Xano, Supabase, and Airtable.

Quick Facts

Category: AI-assisted no-code development
Platform: WeWeb visual development platform
Protocol: Model Context Protocol (MCP)
Named clients: Claude Code, Cursor, Codex, Antigravity, and ChatGPT
Setup: Configure the MCP client, sign in to WeWeb, authorize access, and select a project
Plan availability: Free plan includes a 14-day WeWeb MCP Server trial; Pro lists unlimited access

WeWeb MCP Alternatives

Speculos

Speculos deploys Claude Code apps to shareable URLs, with private, org-wide or public visibility and team controls for domains, data and cloud deployments.

CreateOS Sandbox

CreateOS Sandbox is an isolated compute environment for running code and agent workloads in Firecracker micro-VMs with private networking and SDK, CLI, or MCP control.

GitBot

GitBot is a local browser workspace for reusable coding bots powered by Claude Code, Codex, or OpenCode, with persistent threads and configurable permissions.

Codex Plugins

Codex Plugins bundle reusable skills, app integrations, and MCP servers into workflows you can install in the Codex app or use from Codex CLI.

Wallie

Wallie is an open-source AI streamer that watches your screen, hears chat, and delivers live commentary in a configurable persona. Runs locally with your own keys.

Make Real

Make Real is a Next.js app that turns hand-drawn wireframes into HTML prototypes with the tldraw SDK and AI models, with canvas sketching and embedded preview.