Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the CiteHawk 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%2Fcitehawk.com%2Fcitehawk" | 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%2Fcitehawk.com%2Fcitehawk" | 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 CiteHawk API.
List the brands a workspace tracks for AI visibility
Pull a daily visibility metrics timeseries with the latest KPIs
Report Visibility and Brand Health scores with their history
Return the recent AI responses, with citations, behind the metrics
Start a white-label prospect scan and check its status
GET STARTED
Expose a Looker Studio schema and daily metric rows for connectors
Patterns agents use CiteHawk API for, with concrete tasks.
★ Agent-Monitored AI Visibility
An AI agent pulls a workspace's visibility metrics, scores, and the cited AI responses behind them through Jentic to monitor how brands show up in AI answers. The API key in the Authorization header scopes every read to one workspace, so the agent cannot read across tenants, and a rule can keep it on the read operations. The agent finds each read by intent and calls it directly.
Pull the latest Visibility score and the AI responses behind it, then flag any drop week over week.
GEO Reporting and Dashboards
A reporting tool pulls the daily metrics timeseries and the latest KPIs for a workspace and feeds a Looker Studio connector using the exposed schema and daily metric rows. CiteHawk returns Visibility and Brand Health scores with history, so the dashboard shows trend, not just a snapshot. Teams use this to report GEO performance to stakeholders.
Fetch the daily metric rows for a date range and build a Visibility trend for the workspace.
White-Label Prospect Scans
An agency starts a white-label prospect scan to show a potential client their AI visibility, then polls the scan by id for status and results. CiteHawk runs the scan under the workspace key and returns the scored output when it finishes. Agencies use this as a lead-generation step before onboarding.
Start a prospect scan for a domain and poll it by id until the results are ready.
8 endpoints — the citehawk api serves one workspace's ai-visibility (geo) data, scoped to the api key in the authorization header so callers never pass a workspace id or read across tenants.
METHOD
PATH
DESCRIPTION
/brands
List tracked brands
/metrics
Daily metrics timeseries and latest KPIs
/responses
Recent AI collection responses
/scores
Latest Visibility and Brand Health scores
/prospect-scans
Start a white-label prospect scan
/prospect-scans/{id}
Prospect scan status and results
/brands
List tracked brands
/metrics
Daily metrics timeseries and latest KPIs
/responses
Recent AI collection responses
/scores
Latest Visibility and Brand Health scores
/prospect-scans
Start a white-label prospect scan
/prospect-scans/{id}
Prospect scan status and results
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the CiteHawk API by hand means sending a workspace-scoped key as a bearer token and knowing that every read is pinned to that one workspace with no workspace id to pass. Through Jentic you install once, import CiteHawk from the API Directory, store the key once, and your agent calls it.
Permission scoping
CiteHawk scopes the key to one workspace, and a rule can further bound your agent to the read operations such as metrics, scores, and brands. You choose the operations it may call, so starting white-label prospect scans is not included unless you add it.
Credential isolation
Your CiteHawk key 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 'get the visibility score for my brand', and Jentic returns the matching CiteHawk 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 CiteHawk API through Jentic.
What authentication does the CiteHawk API use?
The CiteHawk API authenticates with a CiteHawk API key sent as a bearer token in the Authorization header, per its OpenAPI spec. The key scopes every request to the single workspace that owns it, so callers never pass a workspace id and cannot read across tenants. Through Jentic the key is stored encrypted by your own Jentic One instance and injected only at call time.
Can I pull AI-visibility metrics and scores with the CiteHawk API?
Yes. The API lists the brands a workspace tracks, returns a daily metrics timeseries with the latest KPIs, and reports Visibility and Brand Health scores with history. It also returns the AI responses, with citations, that power those metrics.
What are the rate limits for the CiteHawk API?
The OpenAPI spec does not specify rate limits for the CiteHawk API. Check the vendor's documentation at https://www.citehawk.com for current limits before pointing an agent at it.
Can I limit what my agent is allowed to do with the CiteHawk API?
Yes. Write a rule that allows only the read operations, such as metrics, scores, and brands, so the agent reports on visibility but cannot start white-label prospect scans. Because the key is already scoped to one workspace, the agent cannot reach another tenant's data, and every call is logged.
Is there a CiteHawk MCP server?
You don't need an MCP server to give your agent the CiteHawk API. Jentic connects it directly from the API Directory: import it, store your workspace key once, and your agent calls the brands, metrics, and scores operations. You skip loading another server's tool definitions into the agent's context.
How do I pull AI-visibility data through Jentic?
Add the CiteHawk API from the Jentic API Directory and store your workspace key once. Your agent then searches by intent such as 'pull my brand's AI visibility metrics' and Jentic returns the matching operation with its input schema, so it can read the scores and the AI responses behind them. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Pull a workspace's AI-visibility data: tracked brands, a daily metrics timeseries with KPIs, Visibility and Brand Health scores, and the cited AI responses behind them. Start white-label prospect scans, all scoped to the API key's workspace.
Use for: List the brands this workspace tracks, Pull the daily visibility metrics timeseries, Get the latest Visibility and Brand Health scores, Review the AI responses and citations behind a metric
Not supported: Does not run paid search campaigns, publish content, or do classic keyword-rank SEO. Use for AI-visibility (GEO) metrics, scores, and prospect scans only.
The CiteHawk API serves one workspace's AI-visibility (GEO) data, scoped to the API key in the Authorization header so callers never pass a workspace id or read across tenants. It lists the brands the workspace tracks, returns a daily visibility metrics timeseries with the latest KPIs, and reports the workspace's Visibility and Brand Health scores with their history. It also returns the recent AI collection responses, with their citations, that power those metrics, starts white-label prospect scans and reports their status, and exposes a Looker Studio schema and daily metric rows for connectors.
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>