Framer MCP connects compatible AI tools such as Codex, Claude, Cursor, and more to your Framer projects. Your agent can create pages, edit layouts and content, manage CMS collections, review SEO, and combine Framer with tools available in the client. Every change remains editable in Framer.
Build and edit pages
Ask your agent to create new pages or update existing layouts. It can work across desktop, tablet, and phone breakpoints and reuse your project’s styles and components. Open Framer to review the result and make further edits on the canvas.
Manage content and CMS
Ask your agent to create CMS collections and items, update structured content, and import content from sources available to your AI client.
Review SEO and site quality
Ask your agent to inspect metadata, headings, alt text, page structure, and content issues. If you connect an SEO tool such as Ahrefs to your AI client, the client can combine that source with Framer to inform its review.
Work with external tools and data
Your agent can use files, scripts, APIs, research, and other connected tools available in its AI client to work with your Framer project. Access depends on the client you use and the tools and data sources you connect to it.
Create a branch for review
Ask your agent to create a Framer branch and make changes there. Review the result in Framer before you merge the branch or publish.
Get started
Follow Getting started with Framer MCP to connect your AI client to Framer.
Current limitations
Localization support is not available in Framer MCP at launch. For localization workflows, use the local @framer/agent CLI setup.
FAQ
Which AI clients work with Framer MCP?
Any AI client that supports remote Streamable HTTP MCP servers and OAuth can connect to Framer, including Codex, Claude Code, Cursor, Pi, Windsurf, Warp, and Grok.
Does Framer need to stay open?
No. Once connected, your agent can work with projects your Framer account can access while the editor is closed. Open Framer to review the result.
Can Framer MCP work with an existing project?
Yes. Give the agent the full project link and describe the task.
How is Framer MCP different from the local CLI setup?
Framer MCP connects compatible AI tools through a remote MCP server. The existing @framer/agent setup uses a local CLI bridge and currently supports additional workflows, including localization. Both remain supported while Framer MCP reaches feature parity.
Can Framer MCP use other tools and data?
Your AI client can combine Framer with files, APIs, research, and other tools it can access. Available connections depend on the client.
