Skip to main content
Glama

Create Clipform

clipform_create_form

Create a new Clipform (interactive video-style form). Returns a viewer URL and form ID. When connected via an authenticated MCP client (e.g. claude.ai), the form lands directly in the user's workspace. Anonymous sessions get a claim URL to transfer ownership later.

If the user hasn't said what to build yet, offer to build their first form and suggest starting points: lead-gen, feedback, quiz, or something else.

Node types (omit config to use defaults where shown):

  • choice: Single or multiple choice node with predefined options (supports options array). Config: choice ({enable_branching, show_answer_feedback, record_scores}), selection_mode ("single"|"multiple", default: "single"), allow_text_response (boolean, default: false), randomise_options (boolean, default: false), show_option_count (boolean, default: false), option_display ("list"|"letters", default: "list"). Defaults: {"selection_mode":"single","choice":{"enable_branching":false},"randomise_options":false,"show_option_count":false,"option_display":"list"}

  • open: Free-form text responses from users. Config: formats (array of {format, order}), max_recording_seconds (number, default: 120). Defaults: {"formats":[{"order":0,"format":"text"},{"order":1,"format":"audio"},{"order":2,"format":"video"}]}

  • details: Collect several fields on one screen - name, email, phone, address, date, and more. Config: title (string), fields (array of {id, type, label, order, required, is_custom}), description (string), consent_items (array of {id, name, label, order, type, document, require_scroll_to_accept}), Available field IDs: first_name, last_name, email, phone. Defaults: {"fields":[{"id":"first_name","type":"first_name","label":"First Name","enabled":true,"required":true},{"id":"email","type":"email","label":"Email","enabled":true,"required":true}],"consent_items":[]}

  • payment: Collect a payment from respondents inline, charged to a connected Stripe account. Config: amount (number), currency ("usd"|"eur"|"gbp"|"cad"|"aud", default: "usd"), provider ("stripe"|"paddle", default: "stripe"), workspace_integration_id (string), title (string), description (string). Defaults: {"amount":null,"currency":"usd","provider":"stripe"}

  • button: Simple button for acknowledgment or navigation (supports options array). Config: button_text (string, default: "Continue"), button_style ("primary"|"secondary"|"outline", default: "primary")

  • redirect: Redirect users to an external URL. Config: url (string), auto_redirect (boolean, default: true). Defaults: {"url":"","auto_redirect":true}

  • file_download: Provide a file for respondents to download. Config: files (array of {file_name, display_name, file_path, file_size, mime_type}), button_text (string, default: "Continue"), description (string)

  • end_screen: Final screen shown when form is completed. Config: title (string, default: "Thank you!"), message (string, default: "Your response has been submitted."), icon ("tick"|"trophy"|"star"|"crown"|"party"|"none", default: "tick"), show_share_button (boolean, default: false), cta_type ("none"|"restart"|"external_link", default: "none"), cta_text (string, default: "Continue"), cta_url (string). Defaults: {"title":"Thank you!","message":"Your response has been submitted."}

All type definitions and config schemas are derived from @vid-master/config (node-types). Refer to the config descriptions above for the correct keys and shapes. AI-PROTECTED parameters have restrictions noted in their descriptions.

Example: A form that asks a question, collects contact info, then finishes: { title: "Quick Survey", nodes: [ { type: "open", prompt: "What's your biggest challenge?" }, { type: "details", prompt: "Leave your details", config: { fields: [{ id: "first_name", required: true }, { id: "email", required: true }] } }, { type: "end_screen", prompt: "Thanks for your response!" } ] }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNoTags for indexing (e.g. ['quiz', 'trivia', 'arsenal']). Include format, genre, and topics.
nodesYesOrdered list of nodes/steps for the form
titleYesForm title
contextYesDescribe the user's underlying goal in one sentence - not the tool you're calling.
font_familyNoAI-PROTECTED: Only set when the user explicitly requests a specific font.
primary_colorNoPrimary/brand color as 6-digit hex (e.g. '#FF5500'). Used for buttons and accents.
background_colorNoBackground color as 6-digit hex (e.g. '#1A1A2E').
show_step_counterNoShow step counter (e.g. '1/5'). Set true for quizzes.
disable_back_navigationNoPrevent going back. Set true for quizzes.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
planNoPlan and auth context for this session
nodesYesCreated nodes in order - IDs for attach_node_media / update_node
form_idYesForm UUID - pass to follow-up tools
viewer_urlYesForm URL for respondents - a live public URL once authenticated/published, or a scoped preview-only link for an anonymous session
dashboard_urlNoBuilder URL (sign in to edit)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / nodes / items / properties / type / enum
      Previous value: -[
      -  "choice",
      -  "open",
      -  "details",
      -  "button",
      -  "redirect",
      -  "file_download",
      -  "end_screen"
      -]New value: +[
      +  "choice",
      +  "open",
      +  "details",
      +  "payment",
      +  "button",
      +  "redirect",
      +  "file_download",
      +  "end_screen"
      +]
  2. Changed1 schema field changed
    • changedInput schema / properties / nodes / items / properties / options / items / properties / score / description
      Previous value: -"Score value for this option (for scored quizzes). Use 1 for correct, 0 for wrong. Scored options automatically enable correct-answer marking (record_scores) on the node."New value: +"Score value for this option (for scored quizzes). Use 1 for correct, 0 for wrong. Scored options automatically enable correct-answer marking (record_scores) and correct/incorrect answer feedback on the node; set config.choice.show_answer_feedback: false to hide the feedback."
  3. Changed2 schema fields changed
    • addedInput schema / properties / nodes / items / properties / options / items / properties / is_correct
      Added value: +{
      +  "description": "Mark this as the correct answer for a quiz (maps to score 1; other options score 0). Use this OR score, not both.",
      +  "type": "boolean"
      +}
    • removedInput schema / properties / nodes / items / properties / options / items / properties / scores
      Removed value: -{
      -  "additionalProperties": {
      -    "type": "number"
      -  },
      -  "description": "Planned feature - category-based scores keyed by category name. Not yet editable in the dashboard.",
      -  "type": "object"
      -}
  4. Changed3 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / context
      Added value: +{
      +  "description": "Describe the user's underlying goal in one sentence - not the tool you're calling.",
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "title",
      -  "nodes"
      -]New value: +[
      +  "title",
      +  "nodes",
      +  "context"
      +]
  5. Changed1 schema field changed
    • changedOutput schema / properties / viewer_url / description
      Previous value: -"Live form URL for respondents"New value: +"Form URL for respondents - a live public URL once authenticated/published, or a scoped preview-only link for an anonymous session"
  6. Changed1 schema field changed
    • changedInput schema / properties / nodes / items / properties / type / enum
      Previous value: -[
      -  "choice",
      -  "open",
      -  "details",
      -  "draw",
      -  "button",
      -  "redirect",
      -  "file_download",
      -  "end_screen"
      -]New value: +[
      +  "choice",
      +  "open",
      +  "details",
      +  "button",
      +  "redirect",
      +  "file_download",
      +  "end_screen"
      +]
  7. Changed2 schema fields changed
    • changedInput schema / properties / nodes / items / properties / type / enum
      Previous value: -[
      -  "choice",
      -  "open",
      -  "contact",
      -  "draw",
      -  "button",
      -  "redirect",
      -  "end_screen"
      -]New value: +[
      +  "choice",
      +  "open",
      +  "details",
      +  "draw",
      +  "button",
      +  "redirect",
      +  "file_download",
      +  "end_screen"
      +]
    • changedOutput schema / properties / nodes / description
      Previous value: -"Created nodes in order - IDs for upload_node_media / update_node"New value: +"Created nodes in order - IDs for attach_node_media / update_node"
  8. First observed

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations are minimal (readOnlyHint false, destructiveHint false), so the description carries the burden. It adds genuinely useful behavior: the workspace-vs-claim-URL delivery difference between authenticated and anonymous sessions, and the note about AI-PROTECTED parameters. These go beyond what annotations declare. The return of a viewer URL and form ID is also additive, though an output schema exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long, but the complexity justifies it — eight node types each with config shapes and defaults cannot be compressed much further. It front-loads the core purpose and returns, uses structured bullets per node type, and closes with a concrete example. Every section earns its place; the verbosity is necessity, not padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with 9 parameters and 8 node types, the description is thorough: purpose, returns, auth-dependent behavior, full config documentation, an example, and a pointer to clipform_get_guide for craft guidance. The output schema covers return values, so not restating them is acceptable. No significant gaps remain for a capable agent to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds substantial meaning beyond the schema: it documents every node type's config keys, shapes, and defaults (choice, open, details, payment, button, redirect, file_download, end_screen), and explains the score/is_correct mapping for options — detail the schema defers to this description. This meaningfully raises agent competence in crafting correct node configs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Create a new Clipform (interactive video-style form)' and what it returns (viewer URL and form ID). The word 'new' distinguishes it from sibling mutation tools like clipform_update_form, clipform_import_form, and clipform_add_node without needing to open their schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context: explains authenticated vs anonymous session behavior and instructs the agent to offer to build a first form with suggested starting points when the user is vague. However, it never names alternatives (e.g., clipform_update_form for modifying, clipform_import_form for importing), so exclusion guidance is absent. Clear context but no explicit when-not-to-use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.