Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Lorem Picsum 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%2Fpicsum.photos%2Fpicsum" | 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%2Fpicsum.photos%2Fpicsum" | 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 Lorem Picsum API.
Fetch a random placeholder image at any width and height
Request a specific image by id at custom dimensions
Generate a deterministic image from a seed string
Apply grayscale and blur effects through query parameters
List available images with pagination
GET STARTED
Read image metadata by id or seed
Patterns agents use Lorem Picsum API for, with concrete tasks.
★ AI Agent Placeholder Images
An AI agent connected through Jentic can drop filler imagery into a generated layout or preview without a human sourcing stock photos. The agent searches for the image operation, Lorem Picsum returns its input schema, and the agent requests an image at the width and height it needs. This is handy for mockups, email previews, and test fixtures.
Fetch a random placeholder image at 1200 by 630 for a preview card
Deterministic Seeded Images
Generate a stable image from a seed string so the same seed always returns the same picture. This gives tests, snapshots, and shared designs a repeatable image instead of a random one that changes on every request.
Generate a deterministic image from a seed at 400 by 400
Image Metadata Lookup
Read the metadata for an image by id or seed to get its author and original dimensions before using it. The paginated list endpoint enumerates available images so an application can pick from the catalog programmatically.
Retrieve the author and dimensions metadata for an image by id
6 endpoints — the lorem picsum api serves placeholder images at any size with optional grayscale and blur effects.
METHOD
PATH
DESCRIPTION
/{width}/{height}
Random placeholder image
/id/{id}/{width}/{height}
Specific image by id at custom size
/seed/{seed}/{width}/{height}
Deterministic image by seed
/v2/list
List available images
/id/{id}/info
Image metadata by id
/seed/{seed}/info
Image metadata by seed
/{width}/{height}
Random placeholder image
/id/{id}/{width}/{height}
Specific image by id at custom size
/seed/{seed}/{width}/{height}
Deterministic image by seed
/v2/list
List available images
/id/{id}/info
Image metadata by id
/seed/{seed}/info
Image metadata by seed
What agents get from Jentic-routed access to this vendor.
Setup
The Lorem Picsum API needs no key or auth, so there is nothing to wire up. Through Jentic you install once, import Lorem Picsum from the API Directory, and your agent calls it with no account, token, or sign-up step in the way.
Permission scoping
Lorem Picsum is entirely read-only image delivery, so a rule can hold your agent to exactly the image and metadata operations you want. You choose the operations it may call, and because there is no account, there is nothing an agent could change.
Credential isolation
Lorem Picsum needs no API key, so there is nothing sensitive to hold. Jentic runs the image requests from your own infrastructure, and nothing is ever placed in the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'get a random placeholder image' or 'list available images', and Jentic returns the matching Lorem Picsum operation with its input schema so the agent builds the right request.
Alternatives and complements available in the Jentic catalogue.
Specific to using Lorem Picsum API through Jentic.
What authentication does the Lorem Picsum API use?
The Lorem Picsum API requires no authentication per its OpenAPI spec: its endpoints are open, so you can request images and metadata without a key or token. Through Jentic the API is imported like any other and called directly from your own infrastructure.
Can I apply grayscale or blur to a Lorem Picsum image?
Yes. Request an image at the width and height you need, then add the grayscale or blur options as query parameters to transform the result. You can target a random image, a specific image by id, or a deterministic image by seed.
Is there a Lorem Picsum MCP server?
You don't need an MCP server to give your agent Lorem Picsum. Jentic connects it directly from the API Directory: import the API and your agent calls the image and metadata endpoints it needs, with no extra server loaded into its context.
Can I limit what my agent is allowed to do with Lorem Picsum?
Yes. Lorem Picsum only serves images and metadata, so you can allow just the image-fetch and metadata operations your agent needs. There is no account to change, and every call it makes is logged.
What are the rate limits for the Lorem Picsum API?
The OpenAPI spec does not publish specific rate limits. Lorem Picsum is a free placeholder service, so pace your requests reasonably and cache images where you can. Check picsum.photos for current guidance.
How do I fetch a placeholder image with Lorem Picsum through Jentic?
Search Jentic for an intent like 'get a random placeholder image', and it returns the Lorem Picsum image operation with its input schema so your agent calls it with a width and height. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Fetch placeholder images at any width and height, by random, id, or seed, with optional grayscale and blur. Agents can also list available images and read image metadata.
Use for: Get a random placeholder image at 800 by 600, Fetch a specific image by id at custom dimensions, Generate a deterministic image from a seed, List the available placeholder images
Not supported: Does not store, host, or let you upload your own images. Use for fetching placeholder images and their metadata only.
The Lorem Picsum API serves placeholder images at any size with optional grayscale and blur effects. It returns a random image for a requested width and height, a specific image by id, or a deterministic image from a seed string, and exposes metadata for any image by id or seed. A paginated listing endpoint enumerates the available images. The service is open and needs no key, which makes it a quick source of filler imagery for prototypes and layouts.
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>