Install Jentic One Beta

Connect the Privatus Analytics API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Privatus Analytics 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%2Fprivatusanalytics.com%2Fprivatusanalytics" | sh

Step 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%2Fprivatusanalytics.com%2Fprivatusanalytics" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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.

Capabilities

What an agent can do with Privatus Analytics API.

Pull headline metrics, time series, and top values of a dimension such as page, channel, or country for a site and period, with comparison periods

Report goal completions, conversion rate, and value, and create goals by kind such as page, event, engagement, outbound, or download

Build funnels from ordered steps and read step counts, conversion, and drop-off

Ask a plain-English question about a site's analytics and read the answer with the queries behind it

GET STARTED

Start building with Privatus Analytics API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Privatus Analytics API for, with concrete tasks.

★ Agent-run weekly traffic summary

An AI agent asked how a site did last week can pull the numbers itself instead of you opening the dashboard. Through Jentic the agent searches for 'get website traffic for a period', calls stats_aggregate with a period and compare setting for the site, then stats_breakdown for the page and channel dimensions, and insights_get for notable changes in plain English. It writes a short summary with the comparison already computed.

GET /sites/{site_id}/stats/aggregate.json with period 7d and compare previous_period, then GET /sites/{site_id}/breakdown/{dimension}.json for dimension 'channel', and summarise the changes

Conversion tracking with goals and funnels

A growth workflow can define what counts as a conversion and track it over time. goals_create takes a name and kind with matching rules such as pattern, event_name, scroll_threshold, or time_threshold_seconds, and funnels_create takes a name and ordered steps with an order_mode and window. The goal and funnel reports then return completions, conversion rate, drop-off, and time between steps for any period.

POST /sites/{site_id}/funnels.json with name 'Signup' and steps for the pricing page, signup page, and signup event, then GET /sites/{site_id}/funnels/{id}.json for the last 30 days

Asking questions of your analytics

Instead of building a query, a developer can ask the built-in assistant. assistant_ask takes a question for a site and starts a conversation, assistant_ask_followup continues it, and assistant_conversations_get returns the questions, answers, and the queries behind each answer, so the agent can show its working. The spec notes these calls count toward a monthly allowance.

POST /sites/{site_id}/ask.json with question 'Which pages lost the most visitors this week?' and return the answer

Site health: audits and uptime

The same API that reports traffic can also check the site is healthy. site_audit_run starts an audit, site_audit_get returns its score and top issues, and site_audit_issues_get explains why a check matters and how to fix it. uptime_checks_create adds a check with a url, kind, and interval_seconds, and status pages publish the results publicly.

POST /sites/{site_id}/audit.json, then GET /sites/{site_id}/audit/issues.json and list the three checks affecting the most pages

Key Endpoints

525 endpoints — the privatus analytics api exposes every page of the privatus analytics web analytics product as json: add .

METHOD

PATH

DESCRIPTION

GET

/sites/{site_id}/stats/aggregate.json

Headline metrics for a period

GET

/sites/{site_id}/stats/timeseries.json

Metrics per time bucket

GET

/sites/{site_id}/breakdown/{dimension}.json

Top values of a dimension

GET

/sites/{site_id}/goals.json

List goals with conversions

GET

/sites/{site_id}/funnels/{id}.json

Funnel report

POST

/sites/{site_id}/ask.json

Ask a question about a site

GET

/sites/{site_id}/live.json

Live visitors and activity

POST

/sites/{site_id}/audit.json

Start a site audit

GET

/sites/{site_id}/stats/aggregate.json

Headline metrics for a period

GET

/sites/{site_id}/stats/timeseries.json

Metrics per time bucket

GET

/sites/{site_id}/breakdown/{dimension}.json

Top values of a dimension

GET

/sites/{site_id}/goals.json

List goals with conversions

GET

/sites/{site_id}/funnels/{id}.json

Funnel report

POST

/sites/{site_id}/ask.json

Ask a question about a site

GET

/sites/{site_id}/live.json

Live visitors and activity

POST

/sites/{site_id}/audit.json

Start a site audit

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring Privatus Analytics by hand means minting a workspace API token, sending it as a bearer header, and learning which of hundreds of .json routes and shared period, compare, and filters parameters answer a given question. Through Jentic you install once, import Privatus Analytics from the API Directory, store the token once, and your agent calls it.

Permission scoping

Privatus puts the site id in the URL path (/sites/{site_id}/...), so a rule can pin your agent to one site's reports. You choose the operations it may call, so destructive ones like events_delete, api_tokens_delete, or site audit mutes are not included unless you add them.

Credential isolation

Your Privatus Analytics token is stored once, encrypted, by your own Jentic One instance and injected into 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 'get website traffic for a period' or 'list goal conversions', and Jentic returns the matching Privatus operation with its input schema, including period and compare, so the agent finds the right route among the full surface.

FAQs

Specific to using Privatus Analytics API through Jentic.

What authentication does the Privatus Analytics API use?

Per its OpenAPI spec, the Privatus Analytics API authenticates with an API token sent as a bearer token in the Authorization header. You create tokens per workspace, and the token value is returned once at creation. Some routes are public endpoints that need no credential, such as the tracking and survey collection routes, public status pages, shared links, docs, and the free tools. Through Jentic the token is held by your own instance and attached at call time.

Can I compare this week's traffic with last week's using the Privatus Analytics API?

Yes. GET /sites/{site_id}/stats/aggregate.json returns headline metrics for a period, and its compare, compare_from, compare_to, and match_weekday parameters add a comparison. The same period, filters, and segment_id parameters apply to the time series, breakdown, referrers, goals, and funnels reports.

What are the rate limits for the Privatus Analytics API?

The OpenAPI spec does not state one global rate limit. Individual operations describe their own, for example warehouse destination uploads are limited to 30 per hour per workspace and webhook tests are rate limited per workspace, with 429 returned when called too often. Check https://privatusanalytics.com/docs for current limits.

Is there a Privatus Analytics MCP server?

You don't need an MCP server to give your agent Privatus Analytics. Jentic connects it directly from the API Directory: import it, store your token once, and your agent discovers the stats, goals, and audit operations on demand instead of loading every operation into its context.

How do I read a site's top pages through Jentic?

Search Jentic for 'top pages on my website', load stats_breakdown, and execute it with the site_id, dimension set to page, and a period. The response lists the top values with their metrics. 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 Privatus Analytics API?

Yes. Write a rule that allows only the GET report operations under /sites/site_123/, such as stats_aggregate, stats_breakdown, goals_list, and funnels_get, so the agent can read that one site's analytics but cannot delete events, revoke API tokens, or change other sites. Every call it makes is logged for review.

Privatus Analytics API

AI ReadinessFoundational (C-)52/100

See full scorecard

Official vendor OpenAPI document · agent-readyAnalyticsWeb Analyticsbearer525 EndpointsREST

For Agents

Read website traffic, conversions, and funnels for any period, compare it with the previous one, and ask plain-English questions about a site's analytics. Also runs site audits, uptime checks, experiments, and email reports.

Use for: Get last week's visitors and pageviews for my site compared with the week before, Find the top referrers sending traffic this month, List all goals with their conversion rates for the last 30 days, Check whether the signup funnel drop-off changed

Not supported: Does not run ad campaigns, host websites, or provide in-app product analytics such as session replay or feature flags. Use for website traffic analytics, conversions, and site health only.

The Privatus Analytics API exposes every page of the Privatus Analytics web analytics product as JSON: add .json to a dashboard URL and send an API token as a bearer token. Per site it returns headline metrics, time series, and top values of a dimension such as page, channel, or country for a chosen period, with comparison periods, filters, and saved segments. Goals, funnels, events, journeys, referrers, click maps, live visitors, and Search Console data sit alongside a plain-English Ask assistant, A/B experiments, site audits, uptime checks and status pages, scheduled email reports, data exports, and testimonial collection forms.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: D-Signals: 4

70%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: B-Signals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

50%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: C-Signals: 4

46%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

58%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: D-Signals: 1

43%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: B-Signals: 1

60%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: ASignals: 1

83%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Privatus Analytics API to your agent

Capabilities

Start building with Privatus Analytics API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Privatus Analytics API

Jentic AI Readiness Score

Privatus Analytics API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness