Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Clypmint API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fclypmint.com%2Fclypmint" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fclypmint.com%2Fclypmint" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Clypmint API.
Browse the available video styles
Copy a style from a reference video link
Start a video edit and get a private upload link for your source video
Check a video or an upload by its id until it is ready
Request a change to a finished video in plain words
GET STARTED
List your recent videos and read your account profile
Patterns agents use Clypmint API for, with concrete tasks.
★ Agent-Driven Video Creation
An AI agent starts a video edit through Jentic, uploads the source to the private link it gets back, and polls the video by id until it is ready, then requests changes in plain words. The bearer key authenticates the write operations while styles can be browsed openly, and a rule can keep the agent on creating and checking videos. The agent finds each operation by intent and calls it directly.
Start a video edit with a chosen style, upload the source to the returned link, and poll the video by id until it is ready.
Style-Based Video Templating
A tool browses the available styles and copies a style from a reference video link so new videos match a consistent look. Clypmint lists styles and creates a new style from a reference, which later edits can reuse. Teams use this to keep a repeatable visual style across many videos.
Copy a style from a reference video link and start a new video edit using that style.
Iterative Video Revisions
After a video is finished, a workflow asks for changes in plain words and checks the updated video by id until the new version is ready. Clypmint accepts a plain-language change request against a finished video and reprocesses it. Teams use this to refine a video without re-specifying the whole edit.
Request a shorter intro on a finished video and poll it by id until the revised version is ready.
8 endpoints — the clypmint api creates and revises short videos from styles.
METHOD
PATH
DESCRIPTION
/styles
List styles
/styles
Copy a style from a reference video link
/videos
List recent videos
/videos
Start a video edit and get an upload link
/videos/{id}
Check a video or an upload
/videos/{id}/changes
Request a change to a finished video
/me
Get the account profile
/styles
List styles
/styles
Copy a style from a reference video link
/videos
List recent videos
/videos
Start a video edit and get an upload link
/videos/{id}
Check a video or an upload
/videos/{id}/changes
Request a change to a finished video
/me
Get the account profile
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Clypmint API by hand means sending a bearer token (an API key or OAuth token), starting an edit to get a private upload link, and polling a video by id until it is ready. Through Jentic you install once, import Clypmint from the API Directory, store the token once, and your agent calls it.
Permission scoping
Clypmint puts the video id in the URL path, so a rule can pin your agent to starting and checking videos and the operations you pick. You choose what it may call, so copying styles or reading the account profile is not included unless you add it.
Credential isolation
Your Clypmint token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'start a video edit' or 'check a video', and Jentic returns the matching Clypmint operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Clypmint API through Jentic.
What authentication does the Clypmint API use?
The Clypmint API authenticates with a bearer token in the Authorization header, which can be an API key or an OAuth token, per its OpenAPI spec. The styles list and the OpenAPI document can be read without a key, while creating and checking videos use the token. Through Jentic the token is stored encrypted by your own Jentic One instance and injected only at call time.
Can I create and revise videos with the Clypmint API?
Yes. You start a video edit and get a private upload link, check the video by its id until it is ready, and then ask for a change to the finished video in plain words. You can also browse styles and copy a style from a reference video link.
What are the rate limits for the Clypmint API?
The OpenAPI spec does not specify rate limits for the Clypmint API. Check the vendor's documentation at https://clypmint.com for current limits before pointing an agent at it.
Can I limit what my agent is allowed to do with the Clypmint API?
Yes. Write a rule that allows only starting and checking videos, so the agent can create and track a render but not copy styles or read your account profile. Each video id is in the URL path, so the rule binds to the video operations, and every call it makes is logged.
Is there a Clypmint MCP server?
You don't need an MCP server to give your agent the Clypmint API. Jentic connects it directly from the API Directory: import it, store your token once, and your agent calls the style and video operations. You skip loading another server's tool definitions into the agent's context.
How do I create a video through Jentic?
Add the Clypmint API from the Jentic API Directory and store your token once. Your agent then searches by intent such as 'start a video edit' and Jentic returns the matching operation with its input schema, so it can start the edit and poll the video until it is ready. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Browse video styles, start a video edit to get a private upload link, check a video until it is ready, and request plain-language changes to a finished video. Authenticated with a bearer API key or OAuth token.
Use for: Start a video edit and get an upload link, Check whether a video has finished rendering, Browse the available styles for a video, Copy a style from a reference video link
Not supported: Does not host live streams, transcode arbitrary files, or manage ad placement. Use for creating, checking, and revising Clypmint videos from styles only.
The Clypmint API creates and revises short videos from styles. It lists available styles and can copy a style from a reference video link, lists your recent videos, and starts a video edit that returns a private upload link for your source video. You check a video or an upload by its id until it is ready, then ask for a change to a finished video in plain words. The account profile endpoint returns your account details.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>