Cirrela AI video generator
Server Details
AI videos with sound from a sentence, one free a day, and Santa video wishes that say any name.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 10 tools
The four create_* tools have very different semantics that the names hide: create_image/create_video actually render and spend credits, while create_ad/create_film/make_wish render nothing and only return a pre-filled web link. An agent can easily pick create_video when it wants an ad, or create_ad when it expects a finished file. The templated trio (ad, film, wish) is otherwise reasonably distinguished by their descriptions.
All names are snake_case verb_noun (create_*, get_*, list_*, estimate_cost, touch_up), which is predictable. Minor deviation: make_wish uses 'make' where the sibling tools use 'create', and touch_up/lookups mix get_/list_. The pattern is still readable throughout.
10 tools is well within a healthy range for a video-generation server. Each tool maps to a distinct capability: two generation types, polling, cost, balance, models, three templated flows, and one post-production flow.
Core lifecycle is covered (create, poll, cost, balance, models, post-production), but there is no way to list past generations or find a video id after the session ends, and no cancel or delete operation for a queued/running render. touch_up depends on an id the agent may have no tool to retrieve, which is a real dead end.
Available Tools
10 toolscreate_adPrepare a product video adAInspect
Prepares video ads for a product, one per format (vertical 9:16 for Reels and TikTok, square 1:1, wide 16:9), from the product's page (Shopify, Amazon, Etsy or any shop) or its name. Returns the link to Cirrela's product-ad page filled in: the page reads the product when the person taps Import, shows the start images and the cost before anything is spent. This tool fetches nothing and renders nothing. Fits "make an ad for my product", "fais une pub vidéo pour mon produit", "haz un anuncio en vídeo de mi producto", "faça um anúncio em vídeo do meu produto".
Inputs: product, language, product_url.
create_filmPrepare a short film from a sentenceAInspect
Prepares a short film from one sentence: 3 to 6 shots, about 15 to 30 seconds, the same character throughout, with sound, music and editing. Returns the link to Cirrela's Film page with the idea filled in, where the person gets story ideas and a storyboard, sees the cost in credits, and makes the film with one tap after signing in. Nothing is rendered or spent in the chat, and no sign-in is needed to get the link. Fits "make a video of…", "fais une vidéo de…", "haz un vídeo de…", "faça um vídeo de…" when the person wants a little story rather than one clip.
Inputs: idea (required), language.
create_imageCreate an imageADestructiveInspect
Starts making one or more images and spends their credits (refunded if it fails). Poll get_generation with the id.
Inputs: prompt (required), tier, image, model, +7 more.
create_videoCreate a videoADestructiveInspect
Starts rendering a video and spends its credits (refunded if it fails). Returns at once with an id: poll get_generation until it is completed.
Inputs: prompt (required), tier, image, model, +8 more.
estimate_costEstimate costARead-onlyIdempotentInspect
What a video or image would cost in credits, and whether the balance covers it. Spends nothing.
Inputs: prompt (required), tier, type, model, +6 more.
get_balanceGet credit balanceBRead-onlyIdempotentInspect
The account's plan, credit balance and limits (renders at once, per day, top resolution).
Inputs: no named parameters.
get_generationGet a creationARead-onlyIdempotentInspect
Status (queued, running, completed, failed), progress and, once completed, the download URLs of a creation.
Inputs: id (required).
list_modelsList models and pricesBRead-onlyIdempotentInspect
The quality tiers (quick, great, cinema) and every model, with their options and prices in credits.
Inputs: type.
make_wishMake a personalised video wishAInspect
Prepares a personalised video wish: Santa Claus, Mrs Claus, an elf, Saint Nicholas, the Three Kings, the Tooth Fairy, a birthday bear or another character says a first name and a short message, in the chosen language. Returns the link to its page on cirrela.com, already filled in: there the person watches the whole video with the Cirrela mark before deciding anything, and can keep it without the mark with one payment on that page. Nothing is rendered or paid in the chat, and no sign-in is needed. A first name and words only: no photo, no real person's face or voice; the words can't hold a link, an address or a phone number. Fits requests such as "personalised Santa video for my son Leo", "vidéo personnalisée du Père Noël pour Emma", "video personalizado de Papá Noel para Lucía", "vídeo personalizado do Papai Noel para o João". Give the person the link.
Inputs: name (required), language (required), message, occasion, +1 more.
touch_upGet a video ready to postAInspect
Opens one of the connected account's finished videos in Cirrela's "Ready to post" panel: word-by-word captions, music, a voice-over, a new format (9:16, 1:1, 16:9) or a sharper version. Returns the link; the panel shows the exact cost in credits before the click, and the original stays. Needs the person's Cirrela account.
Inputs: id (required), kind.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Generate short AI videos with sound from text prompts, with optional locked characters.
AI character videos from one line: returns a link the user taps. First video free, no account.
AI video generator: make TikTok, Reels and Shorts videos with voiceover and captions, and post them.
Make 2D videos and 3D films from a written brief, in your AIVideo.day account.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceVerified AI video. Describe a video to your AI, get a real file back. Deterministic rendering via headless Chrome, six verification gates, and full read-back. Free and open source.-
- AlicenseNot gradedqualityDmaintenanceTurn words, images, and audio into an animated video with MP4 export.MIT

Rendley MCPofficial
AlicenseNot gradedqualityFmaintenanceGives an AI assistant a full video editor: connect it once, then create and edit video by describing what you want.Apache 2.0- 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
Glama MCP Gateway
Add one secure layer between your agents and this server.