Montik

Save component

save_component

Save an overlay to the library so it can be reused across videos. With a brand kit on the project it goes into that brand's pack (brandId; null = the whole team), which the brand's projects list first. Use {{prop}} placeholders in html/css (HTML-escaped in html) and {{prop_json}} in js. HTML overlays are full-frame transparent pages (project width x height px) laid over the video for the clip's duration. Authoring rules (the exporter seeks the page frame by frame, so motion must be seekable):

Animate with CSS @keyframes / transitions or the Web Animations API. Time 0 = clip start. Do not use setTimeout/requestAnimationFrame for motion.
For JS-driven motion define window.montikSeek = (t, duration) => {...} (e.g. gsapTimeline.seek(t)).
Exit animations: animation-delay: calc(var(--clip-duration) - 0.4s) with fill-mode forwards.
Your project's images: {{media:ID}} (ids from list_media) becomes the image's address, in html, css, js or a prop: . PNG, JPEG, WebP and GIF. A page can show one but can't read its pixels back from a canvas.
Brand variables: --brand-primary --brand-secondary --brand-accent --brand-text --brand-background, --font-heading --font-body, --brand-logo (url). Use them instead of hard-coded colours/fonts.
Lay out in px against the frame (var(--frame-w) / var(--frame-h)); keep text inside safe areas (avoid the top 8% and bottom 15% on vertical video).
No external network requests except fonts already in the library. Emoji render natively.
Design: one message per graphic, set as type in the shot's empty space, in the brand fonts. No eyebrow/kicker labels, pills, emoji, gradient text or white drop-shadow cards unless the brand calls for them; one motion idea per ad, easing out. See the brand-overlays playbook. Check the result with render_frame.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>",
      "html": "<html>"
    },
    "name": "save_component"
  }
}

Input Schema

Name	Required	Description
`id`	No
`js`	No
`css`	No
`html`	Yes
`name`	Yes
`props`	No
`brandId`	No
`duration`	No
`projectId`	No	Project to act on (default: the open one)
`description`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already declare readOnly=false, destructive=false, openWorld=false, and the description is consistent with that while adding substantial context: brandId routing into a brand pack, null meaning team-wide, that the exporter seeks the page frame by frame, and that network requests are blocked. It stops short of stating overwrite/upsert behavior when an id is supplied, which is the key remaining behavioral question for a save tool.

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

Conciseness3/5

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

The purpose is front-loaded and the authoring constraints are bulleted and scannable, but the block is long for a save operation and much of it is design/authoring doctrine that the text itself defers to "the brand-overlays playbook." Several rules (safe areas, no pills/emoji, one motion idea) could live in that playbook rather than the tool description.

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 10-parameter tool with nested objects and no output schema, the description conveys a lot of what an agent needs: frame dimensions, seekability requirements, media and brand-variable references, and a verification step. The gaps are the un-described scalar parameters and the props entry schema, so it is close to but not fully complete.

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

Parameters3/5

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

Schema description coverage is only 10% (only projectId is documented), so the description must carry the load. It does well on the two hardest parameters — brandId ("null = the whole team") and props ({{prop}} / {{prop_json}} placeholder syntax) — but leaves id, name, description, duration, css and js unexplained, and never describes the props entry shape (type/default).

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

Purpose4/5

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

The first sentence gives a specific verb and resource plus the reason for it: "Save an overlay to the library so it can be reused across videos." That is clear and distinct from list_components/get_component, but the description never names update_html_overlay or add_html_overlay, so the create-vs-update boundary is left to inference.

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

Usage Guidelines3/5

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

Usage context is implied by "so it can be reused across videos" and a closing pointer to render_frame for verification, which is genuinely useful. However there is no explicit when-to-use/when-not guidance relative to update_html_overlay or add_html_overlay, and no statement of what happens if the overlay already exists.

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

All Montik tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?