Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Cirrela AI video generator

REMOTE · CIRRELA.COM

AI videos with sound from a sentence, one free a day, and Santa video wishes that say any name.

Available components

+26 this week 64 Trust /100

Last scanned (19 hours ago)

Scores higher than 46% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Design and Media

Recent critical change

Authorization (21 Nov 2026). See the changelog before you install this server.

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability60
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 2500 tokens (~250/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass

Unverified: 1 category

A category scored 0 because we could not verify it: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

What we tested

Checks we ran (12)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +26
    • Authorization: pass → fail ▼ critical
    • Transport: unverified → pass ▲ security
    • Injection markers: unverified → pass ▲ security
    • First check of Judged manipulation: pass security
    • MCP protocol: unverified → pass ▲ functional
    • Tool coverage: unverified → 100 ▲ functional
    • First check of Schema quality: fail functional
    • First check of Destructive annotations: pass functional
    • First check of Schema quality: fail functional
    • First check of Schema quality: good functional
    • First check of Tool coverage: 100 functional
  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 1 Nov 26 38

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://cirrela.com/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=cirrela.com CN=WE1,O=Google Trust Services,C=US 24 Oct 2026 22 Jan 2027 ECDSA 256 ECDSA-SHA256 b545e219b21300ab0e13c0f3cd3fcbe5
SANs: cirrela.com, www.cirrela.com, *.www.cirrela.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of cirrela.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
cirrela.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
content-security-policy default-src 'self'; script-src 'nonce-hWHqhV9pFuZ5fsR0I+tUNA==' 'strict-dynamic' 'self' https://challenges.cloudflare.com; worker-src 'self'; style-src 'self' 'unsafe-inline'; font-src 'self' data:; img-src 'self' data: blob: https:; media-src 'self' blob: https:; connect-src 'self' https://precious-chameleon-259.convex.cloud wss://precious-chameleon-259.convex.cloud https://precious-chameleon-259.convex.site https://media.cirrela.com https://eu.i.posthog.com; frame-src https://challenges.cloudflare.com; frame-ancestors 'none'; form-action 'self' https://accounts.google.com https://github.com https://appleid.apple.com; base-uri 'self'; object-src 'none'; upgrade-insecure-requests
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(self), microphone=(self), geolocation=(), browsing-topics=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://cirrela.com/api/mcp Verified 200
http (plaintext) http://cirrela.com/api/mcp HTTPS enforced 301 https://cirrela.com/api/mcp
MCP tools · 10 exposed · ~2,324 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
create_ad ~207

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".

NameTypeReqDescription
languagestring–Optional: the page's language, usually the one the person writes in. Default en.
productstring–Or, without a page: the product in a few words.
product_urlstring–The product's page, https://…

No output schema declared.

No examples provided.

create_film ~194

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.

NameTypeReqDescription
ideastringyesThe film in a sentence or two: who, where, what happens.
languagestring–Optional: the page's language, usually the one the person writes in. Default en.

No output schema declared.

No examples provided.

create_image ~318

Starts making one or more images and spends their credits (refunded if it fails). Poll get_generation with the id.

NameTypeReqDescription
aspect_ratiostring–Aspect ratio, e.g. "16:9", "9:16" (vertical, for Reels and TikTok) or "1:1".
idempotency_keystring–Retrying with the same key never creates twice.
imagestring–Optional start image: base64 JPEG, PNG or WebP (a data: URL works), under 10 MB.
image_idstring–Optional start image already sent to POST /v1/uploads.
max_creditsinteger–Refuse instead of spending more than this many credits.
modelstring–A model id from list_models, instead of a tier.
num_imagesinteger–Images to make, up to the model's max_images.
photo_consentboolean–Required with an image: true only if the person confirmed they have the right to use it and the people in it agree.
promptstringyesWhat to make, in plain words. @handles use the person's saved characters.
resolutionstring–e.g. "720p" or "1080p" for videos, "2K" for images. Defaults to the tier's.
tierstring–Quality tier: quick (cheapest), great (best value, default), cinema (most realistic). Or give `model` instead.

No output schema declared.

No examples provided.

create_video ~345

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.

NameTypeReqDescription
aspect_ratiostring–Aspect ratio, e.g. "16:9", "9:16" (vertical, for Reels and TikTok) or "1:1".
durationinteger–Seconds, from the model's durations (list_models).
idempotency_keystring–Retrying with the same key never creates twice.
imagestring–Optional start image: base64 JPEG, PNG or WebP (a data: URL works), under 10 MB.
image_idstring–Optional start image already sent to POST /v1/uploads.
max_creditsinteger–Refuse instead of spending more than this many credits.
modelstring–A model id from list_models, instead of a tier.
photo_consentboolean–Required with an image: true only if the person confirmed they have the right to use it and the people in it agree.
promptstringyesWhat to make, in plain words. @handles use the person's saved characters.
resolutionstring–e.g. "720p" or "1080p" for videos, "2K" for images. Defaults to the tier's.
soundboolean–Sound on or off, where the model has a switch. Quick always has sound.
tierstring–Quality tier: quick (cheapest), great (best value, default), cinema (most realistic). Or give `model` instead.

No output schema declared.

No examples provided.

estimate_cost ~245

What a video or image would cost in credits, and whether the balance covers it. Spends nothing.

NameTypeReqDescription
aspect_ratiostring–Aspect ratio, e.g. "16:9", "9:16" (vertical, for Reels and TikTok) or "1:1".
durationinteger–Seconds (videos).
modelstring–A model id from list_models, instead of a tier.
num_imagesinteger–Images per request (images).
promptstringyesWhat to make, in plain words. @handles use the person's saved characters.
resolutionstring–e.g. "720p" or "1080p" for videos, "2K" for images. Defaults to the tier's.
soundboolean–Videos: sound on or off, where the model has a switch.
tierstring–Quality tier: quick (cheapest), great (best value, default), cinema (most realistic). Or give `model` instead.
typestring–Default video.
with_imageboolean–Price it as if a start image were attached.

No output schema declared.

No examples provided.

get_balance ~28

The account's plan, credit balance and limits (renders at once, per day, top resolution).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_generation ~50

Status (queued, running, completed, failed), progress and, once completed, the download URLs of a creation.

NameTypeReqDescription
idstringyesThe id create_video, create_daily_video or create_image returned.

No output schema declared.

No examples provided.

list_models ~43

The quality tiers (quick, great, cinema) and every model, with their options and prices in credits.

NameTypeReqDescription
typestring–Only video or only image models.

No output schema declared.

No examples provided.

make_wish ~772

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.

NameTypeReqDescription
characterstring–Optional: who speaks, if the person chose (santa-cabin or santa-workshop for Santa, mrs-claus, elf, saint-nicolas, king-melchior, tooth-fairy, birthday-bear…). It must belong to the occasion; left ou…
languagestringyesThe language spoken: en, fr, es, pt (Brazil), pt-PT (Portugal), hi, ar or id. Usually the language the person writes in.
messagestring–Optional: the exact words, with the first name in them, at most about 12 seconds spoken. Left out, the page offers the occasion's own words.
namestringyesThe first name the video says, as it should be written (a child's first name is fine; never a surname or an address).
occasionstring–Default santa. The occasion: santa (Santa Claus speaks to a child), nice-list (Santa tells a child they are on the Nice List, always kind), elf-arrival (a Christmas elf tells a child he is back for D…

No output schema declared.

No examples provided.

touch_up ~122

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.

NameTypeReqDescription
idstringyesThe video's id, from create_video or get_generation.
kindstring–Optional: which touch-up the person wants.

No output schema declared.

No examples provided.

Install

How do I install the Cirrela AI video generator MCP server?

Cirrela AI video generator is a hosted endpoint at https://cirrela.com/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · cirrela.com

# add to Claude Code
claude mcp add --transport http com-cirrela-video-generator 'https://cirrela.com/api/mcp'
Common questions

What is the Cirrela AI video generator MCP server?

Cirrela AI video generator is an MCP server listed in the public MCP registry as com.cirrela/video-generator. AI videos with sound from a sentence, one free a day, and Santa video wishes that say any name. This page covers its hosted endpoint (https://cirrela.com/api/mcp).

Is the Cirrela AI video generator MCP server safe to use?

Cirrela AI video generator scores 64 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Cirrela AI video generator MCP server expose?

Cirrela AI video generator exposes 10 tools: get_balance, list_models, estimate_cost, create_video, make_wish, and 5 more. Their descriptions and schemas cost roughly 2,324 tokens of context every time the server is loaded.

Does the Cirrela AI video generator MCP server require authentication?

No. We connected to Cirrela AI video generator without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Cirrela AI video generator MCP server still maintained?

Cirrela AI video generator is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Cirrela AI video generator MCP server?

VerifyMCP ran 12 checks on Cirrela AI video generator, covering TLS certificate, Authorization, HTTPS, HSTS header and 8 more. One item could not be completed, a gap on our side rather than a finding about Cirrela AI video generator: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.