Install Jentic One Beta

Connect the Imejis API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Imejis 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%2Fimejis.io%2Fimejis" | 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%2Fimejis.io%2Fimejis" | 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 Imejis API.

Render a design to PNG, JPEG, WebP, or PDF by design id, overriding dynamic fields with query params or a JSON body

Choose stream, hosted, or signed delivery to get image bytes, a public URL, or an expiring signed URL

Render 1 to 25 items in one POST /bulk call, such as several sizes or the slides of a carousel

Read a design's render endpoint and overridable dynamic fields from its config before rendering

GET STARTED

Start building with Imejis API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Imejis API for, with concrete tasks.

★ AI agent generating images through Jentic

A developer wants their agent to produce on-brand images, such as a blog header with the post title, without wiring the Imejis render host by hand. Through Jentic the agent searches for 'render a design to an image', loads the design config to learn the dynamic fields, then calls the render operation with overrides, with the render key injected at call time. The agent returns a hosted URL ready to embed.

Call GET /designs/v2/{id}/config for the header design, then POST /{design_id} with title set to the post title and delivery=hosted, and return the hosted URL

Bulk social graphics

Marketing teams need the same graphic in several sizes or a set of carousel slides. POST /bulk accepts an items array of 1 to 25 entries, each with a designId, an optional variation size id, and overrides, plus request-level format and delivery defaults. The response gives stored URLs for every render.

POST /bulk with three items that share one designId and use different variation ids, with format set to png, and collect the returned URLs

Background exports with webhooks

Pipelines that render on a schedule avoid holding a connection open. POST /designs/v2/{id}/export/jobs takes a required delivery value and an optional webhookUrl, and returns an exportId and pollUrl. GET /analytics/exports/{exportId} returns the status and the stored URL once ready.

POST /designs/v2/{id}/export/jobs with delivery=signed and a webhookUrl, then GET /analytics/exports/{exportId} until the stored URL is returned

Key Endpoints

13 endpoints — the imejis api renders a saved design to a finished image: pass a design id, override its dynamic fields, and get back a png, jpeg, webp, or pdf.

METHOD

PATH

DESCRIPTION

POST

/{design_id}

Render a design to an image

GET

/{design_id}

Render a design via query params

POST

/bulk

Bulk render many items

GET

/designs/v2

List designs

GET

/designs/v2/{id}/config

Get render endpoint and dynamic fields

POST

/designs/v2/{id}/export/jobs

Queue an async stored export

GET

/analytics/exports/{exportId}

Poll an export job

GET

/analytics/api

Get render usage over time

POST

/{design_id}

Render a design to an image

GET

/{design_id}

Render a design via query params

POST

/bulk

Bulk render many items

GET

/designs/v2

List designs

GET

/designs/v2/{id}/config

Get render endpoint and dynamic fields

POST

/designs/v2/{id}/export/jobs

Queue an async stored export

GET

/analytics/exports/{exportId}

Poll an export job

GET

/analytics/api

Get render usage over time

Why Jentic?

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

Setup

Wiring Imejis by hand means juggling two hosts and two credentials: a dma-api-key for renders on render.imejis.io and an OAuth bearer token for designs and exports on api.imejis.io. Through Jentic you install once, import Imejis from the API Directory, store each credential once, and your agent calls it.

Permission scoping

Imejis puts the design id in the URL path (/{design_id} and /designs/v2/{id}/...), so a rule can pin your agent to one design and the operations you pick. You choose the operations it may call, so bulk renders or background export jobs are not included unless you add them.

Credential isolation

Your Imejis render key and access token are stored once, encrypted, by your own Jentic One instance and injected at execution time. They never enter the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'render a design to an image' or 'bulk render images', and Jentic returns the matching Imejis operation with its input schema, including format and delivery options, so the agent calls the right endpoint directly.

FAQs

Specific to using Imejis API through Jentic.

What authentication does the Imejis API use?

The Imejis API declares two kinds of credential in its OpenAPI spec. Render operations on render.imejis.io use a render API key named dma-api-key, sent as a header or, for GET renders and bulk, as a query parameter. Design, export, usage, and key-listing operations on api.imejis.io use an OAuth 2.0 bearer access token. Through Jentic both are stored encrypted by your own Jentic One instance and injected at call time.

Can I get a shareable link instead of image bytes with the Imejis API?

Yes. Set delivery=hosted for a public URL or delivery=signed for an expiring signed URL on the render call; the default stream returns the bytes. On the account side, POST /designs/v2/{id}/export/signed-url takes expiresIn in minutes for the link lifetime.

What are the rate limits for the Imejis API?

The OpenAPI spec does not specify rate limits, though it notes each export consumes one render from your quota. Check https://imejis.io for current plan limits.

Is there an Imejis MCP server?

You don't need an MCP server to give your agent the Imejis render and export operations. Jentic connects them directly from the API Directory: import the API, store your render key and token once, and your agent calls the operations it needs, discovered on demand without loading extra tool definitions into its context.

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

Yes. As a worked example, allow only GET and POST on /{design_id} for one design id, and the agent can render that design with new values but cannot render other designs, queue exports, or read usage. Every call it makes is logged.

How do I render a design through Jentic?

Search Jentic for 'render a design to an image', load the renderDesignPost operation, and execute it with the design_id, a JSON body of dynamic-field overrides, and optional format and delivery. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Imejis API

AI ReadinessAI-Aware (B)65/100

See full scorecard

Official vendor OpenAPI document · agent-readyMediaImage Processingbearer, apiKey13 EndpointsREST

For Agents

Render an Imejis design to an image with dynamic text and values, in bulk or one at a time, and read designs, render configs, export jobs, and usage.

Use for: Render my social card design with a new title and price, I want a signed URL for a rendered image that expires in a day, Generate the same design in three sizes in one call, List all my Imejis designs

Not supported: Does not edit photos, remove backgrounds, or author new designs through this REST surface. Use for rendering saved Imejis designs to images and tracking exports only.

The Imejis API renders a saved design to a finished image: pass a design id, override its dynamic fields, and get back a PNG, JPEG, WebP, or PDF. Renders run on the render host at render.imejis.io with a dma-api-key, either streamed as bytes or delivered as a hosted public URL or an expiring signed URL, and a bulk call renders 1 to 25 items in one request. The account side at api.imejis.io lists designs, returns a design's render config and dynamic fields, queues background exports with an optional webhookUrl, and reports render usage over time.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

100

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

98%

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: BSignals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

50%

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: D+Signals: 4

44%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

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

54%

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: DSignals: 1

47%

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: A-Signals: 1

74%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Imejis API to your agent

Capabilities

Start building with Imejis API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Imejis API

Jentic AI Readiness Score

Imejis API

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