Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the AtlasYield 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%2Fatlasyield.club%2Fatlasyield" | 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%2Fatlasyield.club%2Fatlasyield" | 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 AtlasYield API.
Read the latest Atlas Score Index scores across the tracked vault catalog
Pull a single vault's 16-factor breakdown, live risk metrics, and route-survival verdict
Score an arbitrary basket of vaults
Build a risk-adjusted portfolio allocation from the index
Check a chain's gas regime with current and trailing percentiles
GET STARTED
Patterns agents use AtlasYield API for, with concrete tasks.
★ Agent Vault Screening
An AI agent connected through Jentic reads the latest Atlas scores and a vault's 16-factor breakdown to screen DeFi vaults by yield, safety, liquidity, and sustainability before a person decides anything. Because the index is read-only and neutral, the agent is surfacing research, not placing trades.
Read the latest scores and return the three safest vaults with their factor breakdowns
Portfolio Construction
A research workflow scores a custom basket of vaults and asks the engine for a risk-adjusted allocation, so an agent can evaluate a proposed mix instead of one vault at a time. The portfolio and basket endpoints turn the raw scores into an allocation view.
Score this basket of vaults and return a risk-adjusted allocation across them
Risk and Gas Monitoring
A monitor reads each vault's live risk metrics and route-survival verdict and checks the per-chain gas regime, so an agent can flag when a vault's risk posture or a chain's gas percentiles move. The trailing percentiles give context for whether a reading is unusual.
Report a vault's live risk metrics and route-survival verdict and the current gas regime for its chain
8 endpoints — the atlasyield api provides read-only access to the atlas score index, a neutral 16-factor scoring of defi vaults across four pillars: yield, safety, liquidity, and sustainability.
METHOD
PATH
DESCRIPTION
/scores
Latest vault scores
/catalog
Tracked vault catalog
/basket
Score a basket of vaults
/portfolio
Build a risk-adjusted portfolio
/vaults/{chainId}/{address}/factors
16-factor breakdown for one vault
/gas
Per-chain gas regime
/scores
Latest vault scores
/catalog
Tracked vault catalog
/basket
Score a basket of vaults
/portfolio
Build a risk-adjusted portfolio
/vaults/{chainId}/{address}/factors
16-factor breakdown for one vault
/gas
Per-chain gas regime
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the AtlasYield API by hand means handling its two rate buckets, deciding whether to send an optional partner key in the x-api-key header, and parsing the 16-factor score payloads. Through Jentic you install once, import AtlasYield from the API Directory, store the partner key once if you have one, and your agent calls it.
Permission scoping
AtlasYield puts the chain id and vault address in the URL path, so a rule can let your agent read scores and factor breakdowns while leaving the portfolio and basket-scoring calls out. The whole API is read-only, so you are choosing which reads the agent may make, not giving it any way to move funds.
Credential isolation
Your AtlasYield partner key, if you use one, 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 'read vault scores' or 'score a basket of vaults', and Jentic returns the matching AtlasYield operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using AtlasYield API through Jentic.
Is there an AtlasYield MCP server?
You don't need an MCP server to give your agent the AtlasYield API. Jentic connects it directly from the API Directory: import it, store a partner key once if you have one, and your agent can read vault scores and metrics straight away, with no extra server to run and no tool definitions to load into the agent's context.
Can I limit what my agent is allowed to do with the AtlasYield API?
Yes. Write a rule that allows reading scores, factor breakdowns, and gas regimes but not the portfolio and basket-scoring calls, so the agent can look up vault research without constructing allocations, and every call it makes is logged. The whole API is read-only, so no rule can make it move funds.
What authentication does the AtlasYield API use?
Every endpoint in the AtlasYield spec is public and keyless. An optional partner key sent in the x-api-key header moves you to a higher rate bucket and unlocks partner-only endpoints, per its OpenAPI spec. Through Jentic the partner key, if you use one, is stored encrypted by your own instance and added at call time, so it never appears in the agent's prompt or logs.
Can I score a basket of vaults with the AtlasYield API?
Yes. The basket-scoring endpoint takes a set of vaults and returns their combined Atlas scores, and the portfolio endpoint turns the index into a risk-adjusted allocation, so an agent can evaluate a custom mix rather than one vault at a time. Each vault also exposes its full 16-factor breakdown.
What are the rate limits for the AtlasYield API?
Public endpoints are limited to 60 requests per minute per IP according to the API's own description; an optional partner key raises that to 100 requests per minute in its own bucket. For current limits and partner access, see the AtlasYield documentation at https://docs.atlasyield.club.
How do I read DeFi vault scores with the AtlasYield API through Jentic?
Import the AtlasYield API from the Jentic API Directory, then have your agent issue a request such as 'read the latest vault scores and show the safest ones'. Jentic matches the intent to the scores and factor-breakdown operations and returns their input schemas so the agent builds the right calls. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Read neutral 16-factor DeFi vault scores, risk metrics, and route verdicts, score a basket of vaults, and build a risk-adjusted portfolio. Every endpoint is public; an optional partner key raises the rate limit.
Use for: Get the latest Atlas scores for the tracked vaults, Show the 16-factor breakdown for a vault, Score this basket of vaults, Build a risk-adjusted portfolio from the index
Not supported: Does not execute trades, custody funds, or give investment advice. Use for reading DeFi vault scores, metrics, and allocations only.
The AtlasYield API provides read-only access to the Atlas Score Index, a neutral 16-factor scoring of DeFi vaults across four pillars: yield, safety, liquidity, and sustainability. You can read the latest scores across the tracked vault catalog, pull a single vault's full factor breakdown, live risk metrics, and route-survival verdict, score an arbitrary basket of vaults, and build a risk-adjusted portfolio allocation from the index. It also reports per-chain gas regimes with current and trailing percentiles. It is research and information, not investment advice.
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>