Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the cloro, 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%2Fcloro.dev%2Fcloro" | 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%2Fcloro.dev%2Fcloro" | 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 cloro API.
Capture ChatGPT's answer text, cited sources, shopping cards, and brand entities for a prompt in a chosen country
Compare how Gemini, Google AI Mode, and Bing AI Mode answer the same prompt and which sources each cites
Pull Google Search organic results and People Also Ask, with the AI Overview added through the include.aioverview flag
Track Google News coverage for a query with titles, sources, dates, and links
GET STARTED
Open a Google product panel from a productResultToken to read merchant offers, specifications, and reviews
Queue up to 500 monitoring tasks in one batch request and poll each result by taskId or receive it by webhook
Check the organization's credit balance and async queue load before starting a large monitoring run
Patterns agents use cloro API for, with concrete tasks.
★ AI Agent Brand Visibility Probe via Jentic
An AI assistant for marketers can report how a brand shows up in generative answers on demand. Through Jentic the agent searches by intent, receives the schema for POST /v1/monitor/chatgpt or another monitor operation, and submits a prompt with a country code to get the answer text, cited sources, and brand entities back as JSON. The bearer token stays in your Jentic One instance, so the model never receives the key.
Search Jentic for 'monitor brand on chatgpt', load the POST /v1/monitor/chatgpt schema, and call it with prompt 'best CRM for startups' and country 'US', then report whether 'HubSpot' appears among the brand entities
Generative Engine Optimisation Monitoring
Marketing teams now optimise for AI answer engines as well as classic search results. The cloro API runs the same prompt against ChatGPT, Gemini, Google AI Mode, and Bing AI Mode and returns each answer with its cited sources, so an agent can compare presence and citation share across engines and feed the result into a GEO dashboard the way rank trackers feed SEO dashboards.
Run the prompt 'top project management tools' with country 'GB' against /v1/monitor/chatgpt, /v1/monitor/gemini, and /v1/monitor/aimode and return the ordered list of brands cited in each response
Google Search and AI Overview Tracking
SEO teams need to see the classic results and the AI Overview on the same query. POST /v1/monitor/google returns organic results, People Also Ask, and related searches, and adds the AI Overview when include.aioverview is set, while /v1/monitor/google/news covers news coverage for the same topic. An agent can then flag when an overview stops citing your site.
Call POST /v1/monitor/google with query 'best running shoes', country 'US', and include.aioverview set to true, then return the domains cited in the AI Overview
Scheduled Bulk Monitoring with the Async Queue
Large prompt sets are better run in the background than one request at a time. POST /v1/async/task/batch accepts up to 500 tasks, each validated independently, with a taskType such as CHATGPT, GEMINI, or GOOGLE_NEWS. The agent polls GET /v1/async/task/{taskId} or takes the result by webhook, and can read GET /v1/credits first to confirm the balance covers the run.
Read GET /v1/credits, submit 50 CHATGPT tasks with taskType and payload through POST /v1/async/task/batch, then poll GET /v1/async/task/{taskId} until each task completes
16 endpoints — the cloro api sends a prompt or query to an ai answer engine or search surface and returns the response as structured json: parsed answer text, cited sources, brand entities, shopping results, and ads, geo-targeted by country.
METHOD
PATH
DESCRIPTION
/v1/monitor/chatgpt
Capture a ChatGPT answer with sources and entities
/v1/monitor/gemini
Capture a Gemini answer with sources
/v1/monitor/google
Google Search results with optional AI Overview
/v1/monitor/aimode
Capture a Google AI Mode answer
/v1/monitor/bing/aimode
Capture a Bing AI Mode answer
/v1/async/task/batch
Submit up to 500 async tasks
/v1/async/task/{taskId}
Poll an async task result
/v1/credits
Read the credit balance
/v1/monitor/chatgpt
Capture a ChatGPT answer with sources and entities
/v1/monitor/gemini
Capture a Gemini answer with sources
/v1/monitor/google
Google Search results with optional AI Overview
/v1/monitor/aimode
Capture a Google AI Mode answer
/v1/monitor/bing/aimode
Capture a Bing AI Mode answer
/v1/async/task/batch
Submit up to 500 async tasks
/v1/async/task/{taskId}
Poll an async task result
/v1/credits
Read the credit balance
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the cloro API by hand means handling its bearer auth, choosing between a sync monitor call per engine and the async task queue, and pacing on X-RateLimit-Remaining because its 429 responses carry no Retry-After. Through Jentic you install once, import cloro from the API Directory, store the key once, and your agent calls it.
Permission scoping
cloro states that one key grants every endpoint, so the key itself cannot be narrowed. Each engine has its own monitor path (/v1/monitor/chatgpt, /v1/monitor/gemini), so a rule can bound your agent to the engines you choose, but async tasks carry the engine in the request body as taskType. You choose the operations it may call, so DELETE /v1/async/queue is not included unless you add it.
Credential isolation
Your cloro key is stored once, encrypted, by your own Jentic One instance and injected as the Authorization header at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'monitor brand on chatgpt' or 'track google ai overview', and Jentic returns the matching cloro operation with its input schema, so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using cloro API through Jentic.
Is there a cloro MCP server?
You don't need an MCP server to give your agent the cloro API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent discovers the monitor and async task operations on demand instead of loading a full set of tool definitions into its context.
Can I limit what my agent is allowed to do with the cloro API?
Yes. Write a rule that allows only POST /v1/monitor/gemini and GET /v1/credits, so the agent can probe Gemini and check the balance it is spending, while the other engines, the async queue, and DELETE /v1/async/queue stay out of its reach, and every call it makes is logged by your self-hosted instance.
What authentication does the cloro API use?
The cloro API authenticates with an API key sent as a bearer token in the Authorization header (Authorization: Bearer <key>), per its OpenAPI spec. Keys are created and revoked in the cloro dashboard. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's context.
Which AI answer engines can I monitor with the cloro API?
The spec has monitor operations for ChatGPT, Google Gemini, Google Search with an optional AI Overview, Google AI Mode, Bing AI Mode, and Google News. GET /v1/countries with the model query parameter lists the countries each provider supports, and GET /v1/states lists US states for state-level targeting.
What are the rate limits for the cloro API?
Per the OpenAPI spec, every authenticated response carries X-RateLimit-Limit and X-RateLimit-Remaining headers, and a 429 comes with one of three codes: RATE_LIMIT_EXCEEDED, CONCURRENCY_LIMIT_EXCEEDED, or QUEUE_LIMIT_EXCEEDED. None of them carries Retry-After, so pace requests from the remaining count. The spec also notes a free tier of 500 monthly credits; see https://cloro.dev for plan limits.
How do I run a multi-engine brand check through Jentic?
Search Jentic for 'monitor brand on chatgpt' and it returns POST /v1/monitor/chatgpt with its input schema, which needs a prompt and a country. Repeat for /v1/monitor/gemini and /v1/monitor/aimode, or submit all three as async tasks with POST /v1/async/task/batch. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Does the cloro API return source citations?
Yes. Monitor responses include the engine's answer text and the sources it cited, along with brand entities and, where the engine shows them, shopping results and ads. That lets you build citation-share reports rather than only mention counts.
For Agents
Send a prompt to ChatGPT, Gemini, Google AI Mode, Bing AI Mode, or Google Search and get the answer, cited sources, and brand entities back as JSON, geo-targeted by country, synchronously or through an async task queue.
Use for: I want to check how ChatGPT answers a question about my product, Compare which sources Gemini and Google AI Mode cite for a topic, Monitor whether the Google AI Overview for a query mentions our brand, Find the latest Google News articles about a competitor
Not supported: Does not handle backlink audits, paid ad campaign management, or social media listening. Use for AI answer engine and Google search visibility monitoring only.
The cloro API sends a prompt or query to an AI answer engine or search surface and returns the response as structured JSON: parsed answer text, cited sources, brand entities, shopping results, and ads, geo-targeted by country. It covers ChatGPT, Google Gemini, Google Search with an optional AI Overview, Google AI Mode, Bing AI Mode, and Google News, plus Google product panels and redirect-link resolution. Longer monitoring runs go through an async task queue that accepts up to 500 tasks per batch request, with polling by task id or a webhook on completion, and a credits endpoint reports the remaining balance.
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>