Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Invokely statistics 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%2Finvokely.ai%2Finvokely" | 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%2Finvokely.ai%2Finvokely" | 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 Invokely statistics API.
Search statistical indicators by keyword
Resolve a place name to a normalized location for querying
Read a single indicator value or a full time series for a place
Compare and rank places on a chosen indicator
Export a time series as CSV for downstream analysis
GET STARTED
Save charts, tables, and datasets to a workspace for reuse
Patterns agents use Invokely statistics API for, with concrete tasks.
★ AI Agent Statistical Lookup
An AI agent connected through Jentic answers data questions by resolving the place a user names, searching for the right indicator, and reading its latest value with the unit, period, and source attached. Normalized places and citable sources mean the agent returns an answer it can attribute rather than a bare number.
Resolve the place 'Germany', then search for a population indicator and read its latest value with the source
Time-Series Analysis and Export
An analyst's agent pulls the full history of an indicator for a place and exports it as CSV for charting or modelling elsewhere. The series operation returns normalized periods so the exported data lines up across indicators.
Retrieve a ten-year time series for an indicator and export it as CSV
Place Comparison and Ranking
To benchmark locations, an agent compares several places on one indicator and ranks a list by it, returning an ordered result with values and sources. This turns a comparison question into a single structured response.
Compare two countries on an indicator and rank a provided list of places by the same indicator
16 endpoints — the invokely statistics api returns official statistics with units, periods, normalized places, and citable sources.
METHOD
PATH
DESCRIPTION
/api/v1/indicators
Search indicators
/api/v1/value
Get one indicator value
/api/v1/series
Get a time series
/api/v1/compare
Compare places on an indicator
/api/v1/rank
Rank places by an indicator
/api/v1/export.csv
Export a series as CSV
/api/v1/catalog
List every indicator
/api/v1/indicators
Search indicators
/api/v1/value
Get one indicator value
/api/v1/series
Get a time series
/api/v1/compare
Compare places on an indicator
/api/v1/rank
Rank places by an indicator
/api/v1/export.csv
Export a series as CSV
/api/v1/catalog
List every indicator
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Invokely statistics API by hand means handling its bearer API key or `x-api-key` header, tracking which endpoints are free versus plan-gated, and shaping each indicator query yourself. Through Jentic you install once, import Invokely from the API Directory, store the key once, and your agent calls it.
Permission scoping
Invokely carries indicator and place selections in query parameters, so rules bound which operations your agent may call, not which indicators it reads. You choose the operations it may use, such as searching indicators and reading values, so the workspace save and delete operations are not included unless you add them.
Credential isolation
Your Invokely API 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 'look up a statistic' or 'compare two places', and Jentic returns the matching Invokely 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 Invokely statistics API through Jentic.
What authentication does the Invokely statistics API use?
The data endpoints authenticate with an API key sent as a bearer token or in the `x-api-key` header, as declared in its OpenAPI spec. The catalog, indicator-definition, and sources endpoints are open and need no key. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time.
Can I compare two places on the same indicator with the Invokely statistics API?
Yes. The compare operation returns values for several places on one indicator, the rank operation orders a list of places by it, and the series operation returns the full history for a single place.
What are the rate limits for the Invokely statistics API?
The OpenAPI spec does not state fixed rate limits; free keys receive a plan-required response on paid data endpoints and can use the open catalog and definition endpoints instead. Check the Invokely documentation at https://invokely.ai for the limits on your plan.
Can I limit what my agent is allowed to do with the Invokely statistics API?
Yes. Write a rule that allows only the read operations such as searching indicators, reading values, and comparing places, so the agent can query data but cannot save or delete workspace items, and every call it makes is logged.
How do I look up a statistic with the Invokely statistics API through Jentic?
Search Jentic for 'look up a statistic', add the Invokely statistics API from the directory, and store your API key once. Your agent resolves the place, searches for the indicator, and reads the value with its source. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there an Invokely statistics API MCP server?
You don't need an MCP server to give your agent the Invokely statistics API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the indicator, value, series, and comparison operations. That keeps extra tool definitions out of the agent's context.
For Agents
Search statistical indicators, resolve places, read single values and time series, compare and rank places, and export series as CSV.
Use for: Search for statistical indicators about population growth, Get the latest value of an indicator for a country, Retrieve a time series for an indicator over several years, Compare two places on the same indicator
Not supported: Does not handle raw data ingestion, dashboard hosting, or user account management. Use for querying statistical indicators and time series only.
The Invokely statistics API returns official statistics with units, periods, normalized places, and citable sources. It lets you search indicators, resolve place names, read a single value or a full time series, and compare or rank places on a chosen indicator. Series can be exported as CSV, and a workspace stores charts, tables, and datasets for reuse.
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>