InstantClips
Server Details
Create branded vertical video ads from ecommerce product URLs or product photos.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- InstantStudioAI/instantclips-mcp
- GitHub Stars
- 0
- Server Listing
- instantclips
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 15 tools
Most tools target a distinct resource+action pair (brand, product, video, video direction, feedback), and the descriptions explicitly signpost the tricky boundaries, such as create_product_from_images vs import_product_from_url and update_video_direction vs redraft_video_direction. The only slight fuzziness is among brand operations (create_brand attaches a new brand to a pending product, set_product_brand attaches an existing one, update_brand edits fields), which an agent could momentarily confuse, but each description disambiguates by precondition and effect.
All 15 tools follow a strict verb_noun snake_case pattern: create_brand, list_brands, update_brand, get_product, update_product, generate_video, rate_video, send_feedback. Multi-word nouns are consistently ordered and the verb set (create/get/list/update/set/redraft/import/generate/rate/send) is used predictably.
15 tools map cleanly onto the domain's resources: brands (4), products (4), videos (2), video direction (2), plus feedback. No tool appears redundant, and the count sits at the top of the well-scoped range without feeling bloated.
The product-to-marketing-video lifecycle is well covered: import/create, read, edit, brand assignment, direction drafting and editing, render, poll, rate, and a feedback escape hatch. Gaps are minor: there are no delete operations for products, brands, or videos, and no explicit way to cancel or retry a render beyond calling generate_video again, but agents can work around these.
Available Tools
15 toolscreate_brandCreate a brand for a productAInspect
Create a brand for a product waiting on brand_decision_required and attach it; then offer its
ideas. Ask the user first: it takes a brand slot. A photos product needs name from the user, and
the voice, market and keywords they give.
Inputs: product_id (required), name, voice, keywords, +1 more. Returns: name, brand, ideas, price, +16 more
create_product_from_imagesCreate a product from photosAInspect
Start a product from photos when it has no page (import_product_from_url when it does). Photos
carry no brand: ask the user which, or pass brand_id. An external AI service then reads the
photos; poll get_product.
Inputs: name (required), brand_id, image_urls, description, +2 more. Returns: name, brand, ideas, price, +15 more
generate_videoGenerate the video (spends credits)ADestructiveInspect
Render the video. SPENDS THE USER'S CREDITS: ask first, with the direction, settings, cost and any
watermark, and pass the cost as expected_credit_cost. External services render it; it gets a
public share page and may send account email.
Inputs: product_id (required), expected_credit_cost (required). Returns: queued, videos, next_step, product_id, +7 more
get_productGet a product and its video directionARead-onlyIdempotentInspect
Read a product: import status, brand decision, photos, the video direction with its settings and
credit_cost, and its videos. Poll every 20-30 s while it imports or drafts. next_step says what
to do now.
Inputs: product_id (required). Returns: name, brand, ideas, price, +16 more
get_videoCheck a video's render statusARead-onlyIdempotentInspect
Check one video's render. next_step says what to tell the user and when to poll again; follow it,
since it knows how long this render has run. Mention a watermark only when watermarked appears.
Done or failed: launched_with is its plan.
Inputs: video_request_id (required). Returns: rating, script, status, page_url, +14 more
import_product_from_urlImport a product from its page URLADestructiveInspect
Start a product from its page URL; returns at once, so poll get_product. It detects the brand, and
an external AI service reads the page into facts and ideas. A store locked to another account is
refused and reported to support.
Inputs: url (required), brand_id. Returns: name, brand, ideas, price, +17 more
list_brandsList the account's brandsARead-onlyIdempotentInspect
The account's brands, the plan's brand limit, and account: credits_remaining and
watermarked: true on a free account. Call it before answering brand_decision_required, so the
user chooses a brand by name.
Inputs: no named parameters. Returns: brands, account, brand_limit, brands_used, +2 more
list_productsList the account's productsARead-onlyIdempotentInspect
The account's products, newest first, including ones made on the website. Use it to find a
product_id you don't have, then get_product. Carries account, as list_brands does.
Inputs: limit, query, brand_id. Returns: count, total, account, products, +1 more
rate_videoRate a finished videoADestructiveIdempotentInspect
Record the user's own verdict on a finished video they have watched: reaction, and optional
issues and comment in their words. Never rate for them, and ask at most once. A second call
replaces the rating.
Inputs: reaction (required), video_request_id (required), issues, comment. Returns: rating, next_step, video_request_id
redraft_video_directionDraft a new creative directionADestructiveInspect
Draft the next video's direction through an external AI service: with none and no idea yet, from
one of the product's ideas we choose; else another take in its format. It overwrites edits:
confirm first. Poll get_product.
Inputs: product_id (required). Returns: ratio, format, drafting, editable, +18 more
send_feedbackTell the InstantClips team about a problem with these toolsAInspect
Send the InstantClips team a note about these tools: one that failed or surprised, or something the user wanted that no tool does. Show the user the note and send it only with their OK. Not for support or ratings.
Inputs: message (required). Returns: sent, next_step
set_product_brandAttach a product to an existing brandADestructiveInspect
Attach a product waiting on brand_decision_required to an existing brand (list_brands), once the
user confirms it belongs there; then offer its ideas (get_product). replace_identity rewrites that brand
for every product on it.
Inputs: brand_id (required), product_id (required), replace_identity. Returns: name, brand, ideas, price, +16 more
update_brandEdit a brand's identityADestructiveIdempotentInspect
Edit a brand's name, voice, target_market or keywords (a new list replaces the old); only
the fields you pass change. Future drafts use them; redraft_video_direction rewrites a direction
already drafted.
Inputs: brand_id (required), name, voice, keywords, +1 more. Returns: name, voice, brand_id, keywords, +5 more
update_productEdit a product's facts, link and photosADestructiveInspect
Edit a product's name, description, price and posted link_url, and add or remove photos; only the
fields you pass change. The direction is drafted from these facts, so redraft_video_direction
after changing them.
Inputs: product_id (required), name, price, link_url, +4 more. Returns: name, brand, ideas, price, +15 more
update_video_directionEdit the video direction and render settingsADestructiveIdempotentInspect
Edit the next video's creative_direction, its idea (creator_note), settings and photos; only the
fields you pass change. Settings are parameters, not direction text. A new idea, length or ratio
rewrites the direction: poll get_product.
Inputs: product_id (required), ratio, resolution, creator_note, +4 more. Returns: ratio, format, drafting, editable, +19 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Make motion-design video ads and AI videos for e-commerce products from your AI assistant.
Make short branded ad and social videos from a product link, script or idea, in your chat.
Create product video campaigns from 1-4 product photos and track them. Requires an API key.
Generate AI UGC video ads from any product URL — avatars, voiceover, OAuth Connect.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceGenerate AI UGC video ads from any product URL in 5 minutes. Realistic AI avatars, natural voiceover, proven ad templates. No actors, no editing, no experience required.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to create and edit vertical 9:16 video ads from a brand’s own footage, a reference ad, or an idea, with storyboard validation, captions, voice-over, sound design, deterministic ffmpeg rendering, and visual quality control.56 PyPI1MIT
- AlicenseAqualityCmaintenanceEnables generating commercial multi-shot product video ads from product image URLs or base64 images across TikTok/Reels, Meta Feed, Square, and YouTube formats. Supports storyboard sequences, multiple variants, status polling with coherence scoring, video listing, and quota checks.7MIT
- AlicenseBqualityBmaintenanceMake UGC-style video ads without filming: tell your AI assistant what to say and get a vertical clip of a realistic actor saying it, ready for TikTok, Reels or Shorts. Pick or describe an actor, choose a voice from samples, and see the price before rendering. It also makes faceless videos from a script or a short brief: narration over an opening animated clip and image scenes.581MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.