Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Open Data Portal - CKAN 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%2Fdati.gov.it%2Fdati-gov" | 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%2Fdati.gov.it%2Fdati-gov" | 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 Open Data Portal - CKAN API.
List every dataset in the Italian national open-data portal
List current datasets together with their resources
List the groups, organizations, licenses, and tags that classify the catalog
Read the full metadata for a single dataset by name or id
Search datasets, resources, and tags by keyword
GET STARTED
Discover which organizations publish open data and under which licenses
Patterns agents use Open Data Portal - CKAN API for, with concrete tasks.
★ Agent-Driven Open Data Discovery
An AI agent answers a research question by searching Italy's open-data catalog, ranking the matching datasets, and reading each one's metadata to find downloadable resources. Because the catalog is keyword-searchable, the agent can go from a plain-language topic to a shortlist of datasets and their resource links without a human browsing the portal.
Search the catalog for datasets matching a topic, then read the metadata of the top result and return its resource download links
Catalog Harvesting
Mirror or index the Italian open-data catalog by listing every dataset, then reading each one's metadata and resources. This feeds a downstream data warehouse or search index that tracks what public-sector data is available and when it changes.
List all packages, then fetch the resources for each so a downstream index can record every available dataset
Publisher and License Analysis
Analyse which organizations publish the most open data and under which licenses by listing organizations, licenses, and tags, then counting the datasets attached to each. This supports open-data transparency reporting over the national portal.
List all organizations and licenses, then report how many datasets each organization publishes
10 endpoints — the open data portal ckan api exposes the catalog behind dati.
METHOD
PATH
DESCRIPTION
/action/package_list
List all datasets
/action/current_package_list_with_resources
List datasets with their resources
/action/package_show
Full metadata for one dataset
/action/package_search
Search datasets by query
/action/resource_search
Search resources
/action/organization_list
List publishing organizations
/action/license_list
List available licenses
/action/tag_search
Search catalog tags
/action/package_list
List all datasets
/action/current_package_list_with_resources
List datasets with their resources
/action/package_show
Full metadata for one dataset
/action/package_search
Search datasets by query
/action/resource_search
Search resources
/action/organization_list
List publishing organizations
/action/license_list
List available licenses
/action/tag_search
Search catalog tags
What agents get from Jentic-routed access to this vendor.
Setup
By hand you obtain an API key, set the Authorization header, learn the CKAN action conventions, and page through large result sets yourself. Through Jentic you connect once from the API Directory and your agent calls the catalog actions by intent.
Permission scoping
Every operation is a read-only CKAN action over a public catalog, so you choose exactly which your agent may call, such as dataset search and metadata reads while leaving out bulk listing. Each call is logged for review.
Credential isolation
Your API key is stored encrypted on your own Jentic One instance and injected into the Authorization header at execution time, never placed in the agent's prompt, logs, or context. You rotate it in one place.
Intent-based discovery
Agents search Jentic by intent such as 'search datasets by keyword' or 'list organizations', and Jentic returns the matching CKAN action 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 Open Data Portal - CKAN API through Jentic.
What authentication does the Dati.gov.it CKAN API use?
The spec declares an apiKey scheme that passes your key in the Authorization header, so each request carries that key. When you connect it through Jentic, your own Jentic One instance stores the key encrypted and attaches it to every call for you.
Can I search the Italian open-data catalog by keyword?
Yes. The CKAN package search endpoint takes a query and returns the matching datasets with their metadata, and separate endpoints search resources and tags. You can also list every dataset outright and read a single dataset's full metadata by its name or id.
What are the rate limits for the Dati.gov.it CKAN API?
The OpenAPI spec does not specify rate limits. Check the official dati.gov.it documentation at https://www.dati.gov.it/ for current usage guidance before running large catalog harvests.
How do I query Italian open data through Jentic?
Add the Dati.gov.it Open Data API from the Jentic API Directory, then have your agent search by intent such as 'search datasets by keyword' and call the matching CKAN action. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit which catalog actions my agent is allowed to call?
Yes. Every operation is a read-only CKAN action, so you grant your agent only the ones it needs, such as dataset search and metadata reads, and leave out the rest. Each call is logged, so you can see exactly which catalog actions the agent used.
Is there a Dati.gov.it open data MCP server?
You don't need an MCP server to give your agent the Dati.gov.it catalog. Jentic connects it directly from the API Directory: import it and your agent can search datasets and read metadata right away, without another server loading tool definitions into its context.
Know of an official OpenAPI document? Contribute it →
For Agents
List and search the datasets, organizations, and tags in Italy's dati.gov.it open-data catalog, and read a dataset's full metadata. Built on the standard CKAN action API.
Use for: List all datasets in the Italian open-data portal, Search for datasets about air quality, Get the full metadata for a specific dataset, I want to see which organizations publish open data
Not supported: Does not host or transform the datasets themselves, and does not cover non-Italian catalogs. Use for discovering and reading open-data metadata on dati.gov.it only.
The Open Data Portal CKAN API exposes the catalog behind dati.gov.it, Italy's national open-data portal, through the standard CKAN action endpoints. You list the datasets, groups, organizations, licenses, and tags that classify the catalog, read the full metadata for a single dataset, and run keyword searches across datasets, resources, and tags. It is a discovery layer over published public-sector datasets, returning the metadata and resource links an agent needs to locate open data.
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>