Clipform

MCP Server

Use Clipform from AI assistants like Claude, ChatGPT, Cursor, and more.

Clipform has an MCP server that lets AI assistants create and manage forms through conversation. Describe what you want and the assistant builds it - nodes, media, theming, and more.

Connect your AI assistant

Claude (claude.ai)

  1. Go to Settings in the sidebar
  2. Click Connectors then Add custom connector
  3. Enter https://mcp.clipform.io
  4. Authorize access to your Clipform workspace when prompted

ChatGPT

Requires ChatGPT Pro, Team, or Enterprise.

  1. Go to Settings then Connectors
  2. Click Advanced and enable Developer Mode
  3. Click Create connector and enter https://mcp.clipform.io
  4. Authorize access to your Clipform workspace when prompted

Claude Code

Run this in your terminal:

claude mcp add clipform -- npx -y @clipform/mcp-server

This uses the local stdio transport. Forms are created in anonymous mode - use the dashboard link returned with each form to move it into your Clipform account.

Claude Desktop

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "clipform": {
      "command": "npx",
      "args": ["-y", "@clipform/mcp-server"]
    }
  }
}

Forms are created in anonymous mode with the free-tier 3-node limit. Use the dashboard link returned with each form to move it into your account.

Other MCP clients (Cursor, Windsurf, OpenClaw, etc.)

For clients that support OAuth, point them at https://mcp.clipform.io. Discovery, registration, and authentication are handled automatically via RFC 9728, RFC 8414, and RFC 7591.

For clients that use stdio transport (like most desktop tools), use the npx command:

{
  "mcpServers": {
    "clipform": {
      "command": "npx",
      "args": ["-y", "@clipform/mcp-server"]
    }
  }
}

What you can do

Form and node management

ToolDescription
clipform_create_formCreate a new form with nodes, theming, and tags in one call
clipform_get_formView a form and all its nodes
clipform_update_formChange title, live/draft status, or settings
clipform_delete_formDelete an unclaimed form
clipform_add_nodeAdd a node to an existing form
clipform_update_nodeUpdate node text, type, config, or options
clipform_delete_nodeRemove a node (logic chain auto-relinks)

Media and logic

ToolDescription
clipform_upload_node_mediaAttach video or image to one or more nodes (batch, max 10)
clipform_get_node_mediaView a node's media details
clipform_delete_node_mediaRemove media from a node
clipform_attach_audioAttach audio to a still-image node
clipform_set_logicSet branching logic on a node

Creative tools

ToolDescription
clipform_generate_ttsGenerate narration audio with word-level captions
clipform_generate_videoCreate video from images, audio, and captions
clipform_generate_slideshowCreate slideshow videos from images and audio
clipform_search_mediaSearch royalty-free images and videos
clipform_search_musicSearch royalty-free music and ambient sounds
clipform_render_compositionRender a Remotion composition to MP4, PNG, or GIF
clipform_list_compositionsList available compositions and their prop schemas
clipform_list_assetsList available sound effects, animations, and fonts

How authentication works

Remote (claude.ai, ChatGPT, etc.)

When you connect via https://mcp.clipform.io, OAuth 2.1 handles everything:

  1. Your AI client discovers our authorization server automatically
  2. You sign in to Clipform and approve access to a workspace
  3. Tokens are audience-bound to mcp.clipform.io and scoped to mcp only
  4. Forms are created directly in your workspace with your plan tier limits

Anonymous (no auth)

When you run npx @clipform/mcp-server without an API key:

  1. Forms are created in a shared anonymous workspace
  2. The form's UUID acts as the credential - anyone with the ID can edit it
  3. Free-tier limits apply (3 nodes per form)
  4. Use the dashboard link returned with each form to move it into your account

Example

Try this prompt with any connected assistant:

Create a Clipform called "Customer Feedback" with a choice question asking "How would you rate our service?" with options Excellent, Good, Fair, Poor, then an open-ended question asking "Any additional comments?", and finish with an end screen saying "Thanks for your feedback!"

npm package

The MCP server is published as @clipform/mcp-server on npm.