Install Jentic One Beta

Connect the Mutator to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Mutator, 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%2Fmutator.app%2Fmutator" | sh

Step 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%2Fmutator.app%2Fmutator" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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.

Capabilities

What an agent can do with Mutator API.

Start a run of one automation with POST /api/v1/automations/{automationId}/runs, passing an idempotencyKey and an optional dryRun flag

Generate an image or a 3-15 second video clip from a prompt with POST /api/v1/generations, with aspectRatio, up to 4 variations, sound, and caption or comment overlays

Import a reference picture from a URL with POST /api/v1/assets, tagged with a referenceRole of product or location, so a generation can point at it

Track runs across every automation with GET /api/v1/runs, filtering by status such as running, succeeded, or failed, and by automationId

GET STARTED

Start building with Mutator API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Mutator API for, with concrete tasks.

★ Agent-driven content runs through Jentic

A marketing agent can keep a Mutator workspace producing content on cue without anyone opening the dashboard. Through Jentic it finds the run operations by intent, lists automations with GET /api/v1/automations, starts one with POST /api/v1/automations/{automationId}/runs and an idempotencyKey so a retry never double-starts, then polls GET /api/v1/runs/{runId} for each step's output. Because no endpoint publishes, a person still decides what reaches a social account.

Call GET /api/v1/automations, pick the automation named 'Weekly product reel', call POST /api/v1/automations/{automationId}/runs with idempotencyKey 'reel-2026-11-09' and dryRun false, then poll GET /api/v1/runs/{runId} until it finishes

Prompt-to-clip generation with product references

A team needs a quick product clip without building a full automation. POST /api/v1/assets imports a product photo from a URL with referenceRole product, then POST /api/v1/generations asks for a video with a prompt, a duration between 3 and 15 seconds, an aspectRatio, and an optional caption overlay with text, style, and position. The call returns at once and the work runs on a queue, so the agent polls GET /api/v1/generations/{generationId} or waits for a generation.finished webhook.

Call POST /api/v1/assets with idempotencyKey 'asset-sneaker-01' and url of the product photo, then POST /api/v1/generations with kind video, prompt 'sneaker spinning on a white plinth', duration 8, aspectRatio '9:16', caption text 'New drop Friday', and idempotencyKey 'gen-sneaker-01'

Performance reporting on published content

Deciding which automations to keep means knowing what performed. GET /api/v1/analytics returns the same report the Mutator dashboard renders for a days window between 1 and 365, and GET /api/v1/posts lists what actually went out, filterable by platform and automationId. An agent can combine the two into a weekly summary of which automation produced the strongest posts.

Call GET /api/v1/analytics with days 30, then GET /api/v1/posts with limit 100, and summarize performance grouped by automationId

Event-driven handoff with signed webhooks

Polling is wasteful when a downstream system only needs to know that something finished. POST /api/v1/hooks subscribes a targetUrl to one event such as run.finished or post.published, and the response shows a signing secret once that signs every delivery. GET /api/v1/hooks shows what a key is listening for and whether delivery has been given up on, and DELETE /api/v1/hooks/{hookId} stops it.

Call POST /api/v1/hooks with event run.finished and targetUrl 'https://example.com/hooks/mutator', store the returned secret, then confirm with GET /api/v1/hooks

Key Endpoints

19 endpoints — the mutator api drives mutator's content automations from your own systems: it starts automation runs, requests pictures and clips from a prompt, and reports what was produced and how published posts performed.

METHOD

PATH

DESCRIPTION

POST

/api/v1/automations/{automationId}/runs

Start an automation run

GET

/api/v1/runs/{runId}

Get one run with its steps and output

POST

/api/v1/generations

Request a picture or clip

GET

/api/v1/generations/{generationId}

Get a generation's status and output

GET

/api/v1/media/{mediaId}

Get one file with a fresh signed link

GET

/api/v1/analytics

Get the content performance report

POST

/api/v1/hooks

Subscribe to a webhook event

POST

/api/v1/automations/{automationId}/runs

Start an automation run

GET

/api/v1/runs/{runId}

Get one run with its steps and output

POST

/api/v1/generations

Request a picture or clip

GET

/api/v1/generations/{generationId}

Get a generation's status and output

GET

/api/v1/media/{mediaId}

Get one file with a fresh signed link

GET

/api/v1/analytics

Get the content performance report

POST

/api/v1/hooks

Subscribe to a webhook event

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring Mutator by hand means creating a bearer key under Settings, learning which plan unlocks which endpoints, generating idempotency keys for every run and generation, and paging with after and nextCursor. Through Jentic you install once, import Mutator from the API Directory, store the key once, and your agent calls it.

Permission scoping

Mutator puts the automation id in the URL path (/api/v1/automations/{automationId}/runs), so a rule can pin your agent to starting and reading runs for one automation. You choose the operations it may call, so ones that create new content, like generations or asset imports, are not included unless you add them.

Credential isolation

Your Mutator API key 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 Mutator automation run' or 'generate a video clip from a prompt', and Jentic returns the matching Mutator operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Mutator API through Jentic.

Is there a Mutator MCP server?

You don't need an MCP server to give your agent Mutator. Jentic connects it directly from the API Directory: import it, store your Mutator API key once, and your agent calls it. Operations are discovered on demand, so no extra tool definitions sit in the agent's context.

What authentication does the Mutator API use?

Per its OpenAPI spec, every operation uses a Mutator API key sent as a bearer token in the Authorization header. Keys are created in Mutator under Settings, API keys, New key, come with paid plans, and what a key reaches depends on the plan; GET /api/v1 reports what the key can reach. Through Jentic, the key is stored encrypted by your own Jentic One instance and injected at call time.

Can my agent publish posts to social accounts with the Mutator API?

No. The spec states that no endpoint schedules a post, so no key of any scope can make anything reach a social account. A post exists only once a person puts a file in an account's schedule inside Mutator. The API reports what went out through GET /api/v1/posts.

Can I limit what my agent is allowed to do with the Mutator API?

Yes. For example, write a rule that allows only GET /api/v1/runs, GET /api/v1/runs/{runId}, GET /api/v1/media/{mediaId}, and GET /api/v1/analytics. Your agent can then check runs, fetch produced files, and read performance, but it cannot start runs or request new generations, and every call it makes is logged.

What are the rate limits for the Mutator API?

The OpenAPI spec does not specify rate limits. Check https://mutator.app/docs/api for current limits and plan allowances.

How do I start a Mutator automation run through Jentic?

Search Jentic for 'start a Mutator automation run', load the runs.start operation, and call POST /api/v1/automations/{automationId}/runs with an idempotencyKey of 8 to 80 characters. The body also accepts an optional dryRun boolean. Reusing the same idempotencyKey returns the first run instead of starting another. To run it on your own infrastructure, install Jentic One from its GitHub repo.

How do I know when a Mutator generation is done?

POST /api/v1/generations returns at once and the work happens on a queue. Poll GET /api/v1/generations/{generationId} to see whether it finished and what it made, or subscribe to the generation.finished event with POST /api/v1/hooks to be told when it does.

Mutator App Mutator

AI ReadinessFoundational (D-)42/100

See full scorecard

Official vendor OpenAPI document · agent-readyMarketingMarketing Automationbearer19 EndpointsREST

For Agents

Start Mutator content automation runs, generate pictures and short clips from a prompt, fetch the media they produce, and read post history and performance analytics. The API cannot publish to social accounts.

Use for: I need to kick off my product launch automation in Mutator, Generate a vertical video clip of our new sneaker with a caption, Check whether yesterday's automation run succeeded or failed, List all images Mutator made for the spring campaign automation

Not supported: Does not schedule or publish social posts, edit automations, or upload files for publishing. Use for starting Mutator automation runs, generating pictures and clips, and reading their output and performance only.

The Mutator API drives Mutator's content automations from your own systems: it starts automation runs, requests pictures and clips from a prompt, and reports what was produced and how published posts performed. A run is started per automation with an idempotency key and an optional dry run, and each run returns what every step did and what it produced. Direct generations take a kind of image or video, a prompt, and options such as aspect ratio, variations, clip duration, sound, and an on-screen caption or comment overlay, and reference pictures can be imported from a URL first. Nothing in the API schedules or publishes a post: it lists what went out, returns the analytics report the dashboard shows, and delivers signed webhook events such as run.finished and post.published.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

97%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

100%

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

100%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: B+Signals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

75%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: FSignals: 4

12%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

56%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: B-Signals: 1

60%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: D+Signals: 1

48%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Mutator to your agent

Capabilities

Start building with Mutator API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Mutator App Mutator

Jentic AI Readiness Score

Mutator

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness