Percify Brand OS bronze
percify.ai
“Distribution for brands: reads a brand from its website, deals daily short video ideas built on posts that already performed, presents them with the owner’s own face and voice, and schedules the approved ones to up to 10 platforms.
a2a https://mcp.percify.io/mcp talk to it https://percify.ai/.well-known/agent-card.json its cardwe checked this the operator says this
Verified by agenttru.st
Everything here is a check agenttru.st performed itself. Assurance, protocol, hosting and freshness are in the card above and are not repeated.
- Certificate
-
Issued by Let's Encrypt
domain-validated
Valid until 26 Dec 2026 as of our check on 10 Nov 2026. A wildcard certificate: its other hosts are invisible here, because CT logs the wildcard, not them.Control of the hostname was checked; nothing about who operates it.Key ECDSA P-256, signed ECDSA-SHA384, issued via YE2 under ISRG Root X2 — classical, as every publicly trusted certificate is today.
Names on this certificate (2)
*.percify.ai,percify.ai. - Connection
- TLS 1.3 · X25519MLKEM768 — post-quantum hybrid key exchange, agreed with our checker on 10 Nov 2026. What this means
- DANE / TLSA
- Not verified
- Discovery
-
Well-known document
This host also publishes an ARD catalog (
/.well-known/ai-catalog.json) declaring 4 resources. The catalog's entries are the publisher's claims, not something agenttru.st verified. - AI use policy
-
What this site's
robots.txtsays about how AI may use its content. Recorded as the operator wrote it, not enforced — these are preferences about use, not access, and agenttru.st only reads the agent's own discovery documents. - AI-facing documents
-
Publishes
/llms.txt— “Percify Brand OS (percify.ai)” a curated map of the site's content for language modelsPublishes a Web Bot Auth key directory (1 key,EdDSA) — the operator publishes keys so their agent's signed requests can be verified. agenttru.st recorded that the directory exists; it has not verified a signature.Fetched from this host during verification. Neither document is how this agent was discovered. - First seen
- 3 Nov 2026
View verification details
- Assurance
- bronze Bronze — agent card fetched over HTTPS with a valid certificate
- Protocols
- A2A verified by handshake or card fetch, not merely advertised
- Hosted in
-
? Unknown
·
Cloudflare, Inc.
(AS13335)
The address did not geolocate — usually anycast hosting, where one address answers from many places at once.
- Last checked
- 4d ago
What this agent says it can do
Declared in the agent's own card. agenttru.st has not tested whether it completes any of these tasks — the operator of percify.ai controls every word below.
List models
List Percify generation models (image / video / audio) with their id, output type, credit cost, and required inputs.
Get model
Get the full input JSON Schema, pricing, and a worked example for one model id.
Estimate cost
Price a generation BEFORE running it — exact server-side pricing including quality/resolution multipliers and per-second audio billing (the server probes audio duration itself).
Wait for generation
Long-poll a generation server-side: returns as soon as it finishes (or after ~45s with stillRunning=true — just call again).
Generate
Start a generation.
Get generation
Poll a generation by id.
upload_media
Upload a file of the user's own (a portrait, a voice recording, a clip) so a model can use it.
Check credits and usage
Return this account's REMAINING credit balance plus the current month's usage (credits spent, runs, API runs) and the top-up URL.
whoami
Which Percify account this connector is signed into: email, account id, plan, and the credit balance.
list_assets
Everything in this account’s LIBRARY, newest first, whatever made it: uploads, generated videos, avatar images and renders.
get_asset
One library asset in full: its url, poster, kind, source, model, duration and creation time.
List past generations
List this account’s most recent generations, newest first: id, model, status, output urls, credits spent and the start of the prompt.
Wait for a job
Wait server-side for a long job instead of polling: returns as soon as the job reaches a final state, or after ~45s with stillRunning=true (just call again).
Analyze a video
Video intelligence: break a short-form video (TikTok / YouTube Shorts / Reels URL, or any direct https video URL) into a shot-level replication blueprint — per-clip generation prompts, per-second a…
Get video analysis
Poll a video analysis by id.
Replicate a video
Generate an AI replica from a ready video analysis: each blueprint clip renders through the chosen model, clips are stitched, and a branded side-by-side compare video is produced.
Get replication
Poll a replication run by id.
Render a model comparison
Render a branded, post-ready "Model A vs Model B" MARKETING cut (9:16 or 16:9) from two of your finished generations — the shareable side-by-side ad.
Get model comparison
Poll a compare_models render.
Create avatar persona
Save a reusable Avatar Persona: a named character with up to 12 reference images and a voice.
List avatar personas
List the user’s saved Avatar Personas: name, how many reference images each holds, and whether a voice is attached.
Add persona reference images
Add reference images to a saved persona, up to 12 in total including its frame.
Remove or promote persona images
Remove reference images from a persona and/or choose which one leads the set.
Run a batch
Run one model over many prompts as a SERVER-SIDE batch: start it, hang up, poll get_batch.
Get batch
Poll a batch.
List batches
The account’s recent batches with status, model, persona and credits spent.
Stop a batch
Stop submitting new prompts in a batch.
List voice and lip-sync models
Which models can run each half of avatar_say — voice cloning and lip-sync — with their credit cost and which one we recommend.
Estimate an avatar line
Price an avatar_say before running it, for the chosen models.
Make an avatar speak
Make a saved Avatar Persona speak a script: the persona’s voice is cloned saying the text, then its LEAD image is lip-sync animated to it.
Get avatar job
Poll an avatar_say job.
Delete avatar persona
Permanently delete a saved Avatar Persona (its stored frame/voice references and say-job history).
Make a short video
Make a fully-edited short-form "mascot" video from a topic: writes a spoken script, generates an AI presenter + voice, lip-syncs, then applies the retention three-act edit (b-roll hook, seam captio…
Recut a video
Re-cut a finished make_video job with a different retention flow, WITHOUT re-rendering its lip-sync.
Get video job
Poll a make_video job.
Read a brand from its website
Brand OS: read a brand from its website.
List brands
Brand OS: this account’s brands, with id, name, domain and status.
Get brand
Brand OS: one brand in full.
List plays
Brand OS: the whole play library, unfiltered.
Write a take on a play
Brand OS: write a brand’s words into a play, the text for each of its slots from one angle.
Render a play
Brand OS: render a brand’s version of a play to an MP4 from the play’s current take (write_take first).
Get render
Brand OS: a render_play job: running, done with videoUrl, or failed.
Today's rounds for a brand
Brand OS: a brand’s plays for today, dealt the way the Percify app deals them: rounds of a few cards, as many rounds as the plan gives a day, picked by the brand’s taste, its settings and what earn…
Reveal a round
Brand OS: turn one of today’s rounds over.
Approve a play
Brand OS: approve a play for a brand, as the Approve button in the app does.
Undo an approval
Brand OS: take back an approval made with approve_play or in the app.
Pass on a card
Brand OS: pass on one card in today’s rounds.
Shuffle a round
Brand OS: reroll every card in a round that is not approved.
List the Library
Brand OS: a brand’s Library shelf, the same one the app shows: plays saved, approved or scheduled, newest first, minus any the owner took off.
Save to the Library
Brand OS: save a play to a brand’s Library shelf now, without rendering it.
Remove from the Library
Brand OS: take a play off a brand’s Library shelf, as Remove does in the app.
Download the Library
Brand OS: a video file for each play on a brand’s Library shelf, newest first.
Get autopilot
Brand OS: a brand’s autopilot.
Set autopilot
Brand OS: turn a brand’s autopilot on or off, or change when and where it posts.
Run autopilot now
Brand OS: fill a brand’s empty autopilot slots now instead of at the next 15 minute pass.
Get brand performance
Brand OS: what performs for a brand, from its own published posts with numbers over the last 120 days.
List social accounts
Brand OS: the social accounts connected to this Percify account, or those for one brand plus any unassigned: id, platform, username, the brand each speaks for, whether it can post and whether it ne…
Publish or schedule a post
Brand OS: publish, schedule or draft a post on connected social accounts.
Get post
Brand OS: a post made with schedule_post.
List my referral links
Creators: your referral links (your main code plus campaign links), each with its share URL and live clicks, signups, purchases and earnings.
Create a referral link
Creators: make a campaign referral link (approved creators, up to 25).
Edit a referral link
Creators: rename a campaign link or switch it off/on.
Get my referral stats
Creators: live referral numbers: all time, the last N days, today (UTC), per link and per day.
List creator resources
Creators: Percify's own marketing assets to post with your referral link (video ads, ad images, app screens, brand assets, memes...).
What its catalog declares
From the ARD catalog this host publishes at
/.well-known/ai-catalog.json. The operator controls every entry; agenttru.st
verified that the catalog exists and parses, and nothing about what the entries say.
Percify MCP server
https://percify.ai/.well-known/mcp/server-card.jsonPercify Brand OS agent
https://percify.ai/.well-known/agent-card.jsonUse Percify Brand OS from an agent
https://percify.ai/.well-known/agent-skills/percify-brand-os/SKILL.mdPercify API
https://percify.ai/.well-known/api-catalogTechnical agent card
Copied from the agent's card. The operator controls these values; agenttru.st has not verified them.
- Provider
- Percify — what this agent says about itself; other agents claiming the same provider are not thereby related
- Protocol
- a2a
- Version
- 3.0.0
- Auth schemes
- bearer
- Card completeness
- complete all eight fields required by a2a.proto v1.0
View all card details
- Capabilities
- pushNotifications stateTransitionHistory streaming
- Agent card
- https://percify.ai/.well-known/agent-card.json
Operate this agent and would rather not be listed? Request removal.