Install Jentic One Beta

Connect the Iminify API to your agent

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

Compress an image from a file or url at a chosen level such as smart, ultra, or lossless

Resize by width, height, or scale and convert the format, with keep_metadata to retain EXIF

Write AI alt text in a chosen alt_text_language and apply the suggested file name with use_suggested_name

Scan a web page to collect and compress every image it loads, then download the report as CSV or PDF

GET STARTED

Start building with Iminify API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Iminify API for, with concrete tasks.

★ AI agent optimizing site images through Jentic

A developer wants their coding agent to shrink the images in a repo or CMS before deploy without wiring the Iminify client by hand. Through Jentic the agent searches for 'compress an image', loads the createImage operation with its input schema, and sends each image url with level set to smart and format set to webp, with the personal access token injected at call time. It polls each image and downloads the optimized copy when done.

POST /images with url set to the hero image, level set to smart, and format set to webp, poll GET /images/{id} until finished, then GET /images/{id}/download

Page-wide image audits

Site owners want to know how much image weight a page carries and what compression would save. POST /scans takes a url and compression settings, opens the page on Iminify's servers, and compresses every image it loads. The finished scan can be downloaded as a zip of optimized images or a report in CSV or PDF.

POST /scans with url set to https://example.com and level set to smart, poll GET /scans/{id} until finished, then GET /scans/{id}/report.csv

Accessible alt text at scale

Content teams need alt text on every image for accessibility and search. Iminify writes alt text and a suggested file name when alt_text is on, in a language picked with alt_text_language, and POST /images/{id}/alt-text writes it again for an existing image. use_suggested_name renames the optimized copy to the suggestion.

POST /images/{id}/alt-text with alt_text_language set to es and use_suggested_name set to true, then GET /images/{id} to read the new alt text

Key Endpoints

26 endpoints — the iminify api compresses, resizes, and converts images, and writes ai alt text and a suggested file name for each one.

METHOD

PATH

DESCRIPTION

POST

/images

Compress an image

GET

/images/{id}

Get an image

GET

/images/{id}/download

Download an image

POST

/images/{id}/recompress

Compress an image again

POST

/images/{id}/alt-text

Write an image's alt text

POST

/scans

Scan a page

GET

/scans/{id}/report.csv

Download a page report as CSV

POST

/images

Compress an image

GET

/images/{id}

Get an image

GET

/images/{id}/download

Download an image

POST

/images/{id}/recompress

Compress an image again

POST

/images/{id}/alt-text

Write an image's alt text

POST

/scans

Scan a page

GET

/scans/{id}/report.csv

Download a page report as CSV

Why Jentic?

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

Setup

Wiring Iminify by hand means creating a personal access token, sending it as a bearer header, and polling background images and scans until they finish before downloading. Through Jentic you install once, import Iminify from the API Directory, store the token once, and your agent calls it.

Permission scoping

Iminify puts the image or scan id in the URL path (/images/{id}/..., /scans/{id}/...), so a rule can pin your agent to one image or scan and the operations you pick. You choose the operations it may call, so destructive ones like deleteImage or deleteScan are not included unless you add them.

Credential isolation

Your Iminify access 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 'compress an image' or 'scan a page for images', and Jentic returns the matching Iminify operation with its input schema so the agent sets level, format, and size correctly.

FAQs

Specific to using Iminify API through Jentic.

What authentication does the Iminify API use?

The Iminify API authenticates with a personal access token from Settings > API Tokens on iminify.com, sent as a bearer token in the Authorization header, per its OpenAPI spec. The spec adds that the account's email must be verified. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time.

Can I resize and convert an image with the Iminify API?

Yes. POST /images accepts width, height, or scale for resizing, a format to convert to, and a level for compression strength. Send either a file upload or a url. POST /images/{id}/recompress applies new settings to an image you already have.

What are the rate limits for the Iminify API?

The OpenAPI spec says each page scan counts against a daily scan allowance and a per-minute page scan allowance, but it does not give the numbers. Check https://www.iminify.com/docs for the current limits on your plan.

Is there an Iminify MCP server?

You don't need an MCP server to give your agent Iminify. Jentic connects it directly from the API Directory: import it, store your access token once, and your agent calls the compression, scan, and download operations it needs, discovered on demand.

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

Yes. For example, write a rule that allows only POST /images, GET /images/{id}, and GET /images/{id}/download, so the agent can compress and fetch images but cannot delete them, share them publicly, or run page scans. Every call it makes is logged.

How do I compress an image through Jentic?

Search Jentic for 'compress an image', load the createImage operation, and execute it with a url or file and a level such as smart. Poll the getImage operation until it finishes, then call downloadImage. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Iminify API

AI ReadinessAI-Aware (A-)73/100

See full scorecard

Official vendor OpenAPI document · agent-readyMediaImage Processingbearer26 EndpointsREST

For Agents

Compress, resize, and convert images or every image on a web page, generate alt text, and download the optimized files or a scan report.

Use for: Compress this product photo without visible quality loss, I want to resize an image to 1200 pixels wide and convert it to WebP, Scan my homepage and compress every image on it, Write alt text in Spanish for an image

Not supported: Does not host images on a CDN, edit image content, or remove backgrounds. Use for compressing, resizing, converting, and alt-texting images only.

The Iminify API compresses, resizes, and converts images, and writes AI alt text and a suggested file name for each one. An image is created from an uploaded file or a public url with a compression level such as smart, ultra, or lossless, an optional target format, width, height, or scale, and keep_metadata to retain EXIF. Page scans open a web page on Iminify's servers, collect every image it loads, and compress each with the same settings, with reports downloadable as CSV, PDF, or a zip. Work runs in the background, so a client creates an image or scan and polls it until it finishes.

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).

75%

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

22%

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

55%

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: BSignals: 4

62%

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.

91%

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: B+Signals: 1

69%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Iminify API to your agent

Capabilities

Start building with Iminify API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Iminify API

Jentic AI Readiness Score

Iminify 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