Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Rooster Agents — agent 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%2Froosteragents.ai%2Frooster-agents" | 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%2Froosteragents.ai%2Frooster-agents" | 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 Rooster Agents — agent API.
Score a domain from 0 to 100 on the allowed in, discoverable, readable, and callable gates with ranked fixes
Check whether AI answer engines recommend a business against local rivals, filtered by category and city
Run a full answer-engine probe with citation sources, rival share-of-answer, and a remediation plan
List the directory of verified bookable businesses
GET STARTED
Fetch one business's schema.org graph, agent manifest, and booking action by id
Pay for each analysis call in USDC through an x402 402 challenge and X-PAYMENT replay
Patterns agents use Rooster Agents — agent API for, with concrete tasks.
★ AI marketing agent auditing answer-engine visibility
A developer building a marketing agent wants it to tell a local business owner whether AI assistants actually recommend them. Through Jentic the agent searches for 'AI visibility scan', loads Rooster's GET /v1/scan, and passes domain, category, and city. The call is paid per request in USDC over x402, so there is no Rooster account to set up, and the agent reports the score against real local rivals and the first fix to make.
Call GET /v1/scan with domain 'example-bakery.com', category 'bakery', and city 'Austin', complete the x402 payment challenge, and summarise the score and top recommended fix
Agent-readiness check before launch
Before a site goes live, a developer checks whether AI agents can use it at all. GET /v1/agent-readiness scores a hostname from 0 to 100 on four gates (allowed in, discoverable, readable, callable) and returns a ranked list of fixes, which makes a cheap pre-launch check that can be rerun after each change.
Call GET /v1/agent-readiness with domain 'shop.example.com' and list each failed gate with its suggested fix
Competitive answer-engine research
An agency preparing a pitch needs evidence of where a client stands. GET /v1/scan/full runs multi-prompt answer-engine probing and returns citation sources, rival share-of-answer, and a prioritised remediation plan for the domain within its category and city.
Call GET /v1/scan/full with domain 'client-gym.com', category 'gym', and city 'Leeds', then list the top three rivals by share-of-answer
Booking handoff for a consumer agent
A consumer assistant asked to book a service needs a business it can actually transact with. GET /gateway/directory.json lists verified bookable businesses without any credential, and GET /gateway/businesses/{id}.json returns that business's schema.org graph, agent manifest, and booking action for the handoff.
Call GET /gateway/directory.json, pick a business by id, then call GET /gateway/businesses/{id}.json and return its booking action
6 endpoints — the rooster agents api measures how visible a business is to ai answer engines and lets agents discover and book verified real-world businesses.
METHOD
PATH
DESCRIPTION
/v1/agent-readiness
Agent-readiness score for a domain
/v1/scan
AI visibility scan
/v1/scan/full
Full AI visibility scan
/gateway/directory.json
Verified bookable business directory
/gateway/businesses/{id}.json
One business with its booking action
/v1/agent-readiness
Agent-readiness score for a domain
/v1/scan
AI visibility scan
/v1/scan/full
Full AI visibility scan
/gateway/directory.json
Verified bookable business directory
/gateway/businesses/{id}.json
One business with its booking action
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Rooster Agents by hand means splitting calls across two hosts, roosteragents.ai for discovery and a separate metering host for paid scans, and implementing the x402 402-challenge and X-PAYMENT replay yourself. Through Jentic you install once, import Rooster Agents from the API Directory, and your agent calls it by intent.
Permission scoping
Rooster Agents takes the domain, category, and city as query parameters, so limit the agent to the operations it needs, such as the agent-readiness score. You choose the operations it may call, so the more expensive GET /v1/scan/full is not included unless you add it.
Credential isolation
The discovery operations need no credential, and the paid scans settle through x402 payments rather than an account key. Anything you do configure in your own Jentic One instance is stored encrypted and injected at execution time, outside the agent's prompt, logs, and context.
Intent-based discovery
Agents search Jentic by intent such as 'AI visibility scan' or 'find a bookable business', and Jentic returns the matching Rooster Agents operation with its input schema and the host it runs on.
Alternatives and complements available in the Jentic catalogue.
Specific to using Rooster Agents — agent API through Jentic.
What authentication does the Rooster Agents API use?
The Rooster Agents OpenAPI spec declares one scheme, x402, an HTTP scheme for pay-per-call USDC settlement: the server answers with a 402 challenge and the client replays the request with an X-PAYMENT header. It applies to GET /v1/agent-readiness, GET /v1/scan, and GET /v1/scan/full. The directory and business lookups declare no security and need no account.
How much does a Rooster Agents scan cost?
The spec's x-payment-info lists $0.02 USDC for GET /v1/agent-readiness, $0.25 for GET /v1/scan, and $1.00 for GET /v1/scan/full, on the base-sepolia network with a status of testnet-preview. Check the x402 discovery document under /.well-known/x402 on roosteragents.ai for current payment details.
What are the rate limits for the Rooster Agents API?
The OpenAPI spec does not specify rate limits. See https://roosteragents.ai/ for current guidance.
Is there a Rooster Agents MCP server?
Yes - the Rooster Agents spec itself includes a JSON-RPC endpoint at POST /mcp for initialize, tools/list, and tools/call. You can also connect Rooster Agents directly through Jentic: your agent gets the full 6-endpoint surface without loading another server's tool definitions into its context, and your rules decide which operations the agent may call.
How do I run an AI visibility scan through Jentic?
Search Jentic for 'check AI visibility for a business', load the ai_visibility_scan operation (GET /v1/scan), and pass domain, with category and city where known. The response comes back after the x402 payment step completes. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the Rooster Agents API?
Yes. If the agent should only make free lookups, write a rule that allows GET /gateway/directory.json and GET /gateway/businesses/{id}.json. It can then browse and read businesses but cannot start any paid scan, and every call it makes is logged.
For Agents
Score a business domain for AI answer-engine visibility and agent readiness per call over x402, and look up verified bookable businesses with their booking actions.
Use for: Check whether AI assistants recommend my bakery in Austin, Get the agent-readiness score for example-dental.com, I want a full AI visibility report with rival share-of-answer, List all verified bookable businesses in the directory
Not supported: Does not track classic search rankings, run ad campaigns, or complete bookings itself. Use for AI answer-engine visibility scoring and verified business discovery only.
The Rooster Agents API measures how visible a business is to AI answer engines and lets agents discover and book verified real-world businesses. Its paid analysis operations score a domain on four agentic-web gates (allowed in, discoverable, readable, callable), check whether answer engines recommend the business against its local rivals, and run a deeper probe with citation sources, rival share-of-answer, and a prioritised remediation plan. Discovery operations return a directory of verified bookable businesses and, for each one, a schema.org graph, agent manifest, and booking action. Paid calls settle per request in USDC over the x402 protocol, with no account.
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>