Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the EON API - Documentation Device, 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%2Feongroup.co%2Feongroup" | 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%2Feongroup.co%2Feongroup" | 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 EON API - Documentation Device API.
Create and retrieve assets by id, internal id, or content hash
Run OCR on an asset to extract its text content
Organise assets into folders and prepare them for download
Manage facilities and associate assets with a facility
Catalog products, materials, and items as structured records
GET STARTED
Record and aggregate interactions logged against entities
Patterns agents use EON API - Documentation Device API for, with concrete tasks.
★ Agent-Driven Asset Intake
An AI agent connected through Jentic ingests new assets by creating an asset record, running OCR to pull its text, and filing it into a folder. Because EON exposes retrieval by id, internal id, and content hash, the agent can de-duplicate against an existing asset before creating a new one, keeping the catalogue clean.
Create an asset, run OCR on it to extract text, and file it into a folder
Facility Asset Tracking
A facilities team tracks which assets belong where by associating assets with facilities and listing a facility's assets. The EON API manages facilities and the asset associations behind them, so an agent reconciles a facility's expected assets against what is actually recorded.
List the assets associated with a facility and flag any expected asset that is missing
Product and Materials Cataloguing
A product data team keeps a catalogue of products, materials, and items current. The EON API creates and lists these records and the policies and labels tied to them, letting an agent add a new product with its materials and confirm it was recorded correctly.
Create a product, add its materials, and confirm both records resolve on retrieval
192 endpoints — the eon api manages a connected graph of assets, facilities, products, materials, and items on the eon group platform, together with the folders and documents attached to them.
METHOD
PATH
DESCRIPTION
/api/v2/assets/
List assets
/api/v2/assets/
Create an asset
/api/v2/assets/{id}/
Retrieve an asset by id
/api/v2/assets/{id}/ocr/
Run OCR on an asset
/api/v2/facilities/
List facilities
/api/v2/folders/
List folders
/api/v2/products/
List products
/api/v2/interactions/
List interactions
/api/v2/assets/
List assets
/api/v2/assets/
Create an asset
/api/v2/assets/{id}/
Retrieve an asset by id
/api/v2/assets/{id}/ocr/
Run OCR on an asset
/api/v2/facilities/
List facilities
/api/v2/folders/
List folders
/api/v2/products/
List products
/api/v2/interactions/
List interactions
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the EON API by hand means setting both the `Device-Api-Key` and `Api-Secret` headers correctly and finding the right operation among 192 across assets, facilities, products, and materials. Through Jentic you install once, import the EON API from the API Directory, store the keys once, and your agent calls the operations it needs.
Permission scoping
EON puts the asset and facility id in the URL path, so a rule can scope your agent to the operations on one asset or facility. You choose the operations it may call, so destructive ones like asset deletion are not included unless you add them.
Credential isolation
Your EON API keys are held by your own Jentic One instance, encrypted, and injected into the request headers at execution time. They never enter the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'create an asset' or 'run OCR on an asset', and Jentic returns the matching EON operation with its input schema so the agent calls the right endpoint without scanning the full list.
Alternatives and complements available in the Jentic catalogue.
Specific to using EON API - Documentation Device API through Jentic.
What authentication does the EON API use?
The EON API declares two API key headers in its OpenAPI spec: `Device-Api-Key` on almost every operation and `Api-Secret` on the event-handling operation. Through Jentic these keys are held by your own Jentic One instance and attached at execution time, so they never appear in your agent's prompt or logs.
Can I run OCR on an asset with the EON API?
Yes. The asset OCR operation extracts text from an asset you have created, and assets can be retrieved by id, internal id, or content hash. Your agent can create an asset, run OCR to pull its text, and file the result into a folder.
What are the rate limits for the EON API?
The OpenAPI spec does not specify rate limits. Check with EON Group technical support at https://www.eon.xyz/support for the current limits before running high-volume asset operations.
Is there an EON MCP server?
You do not need an MCP server to give your agent the EON API. Jentic connects it directly from the API Directory: import it, store your keys once, and your agent discovers the asset, facility, and product operations it needs on demand without loading an extra server's tool definitions into its context.
Can I limit what my agent is allowed to do with the EON API?
Yes. Write a rule that allows only the read operations your agent needs, such as listing assets and facilities, so it can browse the catalogue but cannot create or delete records across the 192-operation surface, and every call it makes is logged.
How do I manage EON assets through Jentic?
Install the Jentic One command line with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, then add the EON API from the Jentic directory and search by intent such as 'create an asset and run OCR'. Jentic returns the matching operation with its input schema so your agent builds a valid request. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Know of an official OpenAPI document? Contribute it →
For Agents
Manage assets, facilities, products, and materials on the EON platform: create and retrieve records, run OCR on assets, organise folders, and record interactions against entities.
Use for: Create a new asset in the EON platform, Retrieve an asset by its internal id, Run OCR on an uploaded asset to extract text, List the assets associated with a facility
Not supported: Does not handle e-commerce checkout, payment processing, or shipping. Use for managing assets, facilities, and their documentation records only.
The EON API manages a connected graph of assets, facilities, products, materials, and items on the EON Group platform, together with the folders and documents attached to them. Your agent creates and retrieves assets by id, internal id, or content hash, runs OCR to extract text from an asset, and organises assets into folders for download. It also records interactions against entities and administers facilities, policies, and labels so an automation can keep a large asset catalogue current.
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>