Adopt
AI-ready metadata
Updated 3 sections on this page are new or updated since 1.2.0-rc.1 (2026-11-06). Everything that changed
AI-ready metadata answers what an AI team, or an AI system, needs before using data: what it is, whether it may be used for training, how good it is, what it covers, and under what policy. It also lets AI assistants read the profile itself.
What AI-ready means here
Described for machines
Every record converts to JSON-LD, Turtle, schema.org and Croissant. The profile publishes its own shapes, schema and context.
Permission to train, stated
The AI-ready extension makes the owner say whether the data may train, fine-tune or evaluate models. A usage policy says it for machines.
Quality you can see
A quality score on five dimensions, and a link to the data quality report, so models are not trained on data nobody can judge.
An assistant that knows the profile
An MCP server lets AI assistants look up properties, check records and convert them, using the same rules as the shapes.
A map for language models
llms.txt and llms-full.txt at the site root point language models at the profile's content in plain markdown.
Honest limits
The use for AI is the owner's statement. The licence and the law still bind. An AI system must not treat a missing statement as permission.
It follows the Guidelines and best practices for making government datasets ready for AIV.
The AI-ready extension
Makes the record answer the questions an AI team asks first: may we train on it, is it synthetic, where is the data card, what policy applies, how good is it, and what period does it cover. See the extension.
| Property | Class | Obligation | Term | Change | Definition |
|---|---|---|---|---|---|
| Use for AI | Dataset | Mandatory Provisional | dcatuk:aiUse | New | Whether the data may be used to train, fine-tune or evaluate AI models. |
| Personal data | Dataset | Mandatory | dcatuk:personalData | Raised from recommended | Whether the data contains information about identifiable living people, and in what form. |
| Usage policy | Dataset | Recommended | odrl:hasPolicy | Raised from optional | A machine-readable policy, in the W3C Open Digital Rights Language (ODRL), saying what may and may not be done with the resource. |
| Data card | Dataset | Recommended Provisional | dcatuk:dataCard | New | A page that documents how the data was collected, what it contains, what it is for and its known gaps and biases. |
| Synthetic data | Dataset | Recommended Provisional | dcatuk:syntheticData | New | Whether the data was generated rather than collected. |
| Data quality | Dataset | Recommended | dqv:hasQualityAnnotation | Raised from optional | A link to a published statement or measurement of the quality of the data. |
| Time period covered | Dataset | Recommended | dct:temporal | Narrowed | The period of time the data is about. |
| Documentation | Dataset | Recommended | foaf:page | Raised from optional | A web page that documents the resource, such as a user guide or a methodology. |
| Generated by | Dataset | Optional | prov:wasGeneratedBy | New | The process, model or system that generated the data, as an identifier. |
Usage policies machines can readUpdated
Link a policy with usage policy. Each template is ODRL 2.2 in JSON-LD. Purposes such as training AI models are terms this profile adds, and are provisional. Where a licence and a policy disagree, the licence wins. ODRL Information Model 2.2V
| Policy | Type | File |
|---|---|---|
| Open Government Licence v3.0, as a policy: use, copy, share and adapt, with attribution | Set | ogl-open.jsonld |
| Open use with attribution, but not for training AI models | Set | ogl-no-ai-training.jsonld |
| Use only to evaluate AI models, not to train them | Set | ai-evaluation-only.jsonld |
| Use for research only, without sharing further | Set | research-only.jsonld |
| An offer: use under a data sharing agreement | Offer | agreement-required.jsonld |
Exports for search engines and machine learningUpdated
The record builder and the MCP server export any record as schema.org JSON-LD and as Croissant 1.1. The Croissant export is dataset level only: add the record sets (columns and their types) with Croissant tools. Croissant 1.1S
- An open dataset with two files, schema.org and Croissant
- An open event API, schema.org
- An internal API that needs an agreement, schema.org
- A dataset series and one release in it, schema.org
- One release in a series, schema.org and Croissant
- A critical data asset (synthetic), schema.org and Croissant
- A catalogue (synthetic), schema.org
- A harvested catalogue record (synthetic), schema.org
- Personal data shared across borders (synthetic), schema.org and Croissant
- Values left empty on purpose (synthetic), schema.org and Croissant
A map for language modelsUpdated
llms.txt lists the portal’s pages and files for language models, as the llms.txt proposal suggests; llms-full.txt holds every class, property and codelist as plain markdown. The llms.txt proposalV
An MCP server for AI assistants
A small Model Context Protocol server lets an AI assistant look up the profile and check, score, convert and export records. It runs on your machine, uses the portal’s own validator, makes no network requests and writes no files. The repository’s tests start it and call its tools.
python3 -I tools/build.py node integrations/mcp/server.js
| Tool | What it does |
|---|---|
profile_summary | What DCAT-AP-UK is, its version and status, its classes and its sector extensions. |
describe_class | Every property of a class with its obligation (M, R, O, C) and cardinality, optionally with extensions applied. |
describe_property | The definition, guidance, kind, codelist and example of a property, and the classes that use it. |
list_codelist | The values of a codelist, with their identifiers. |
search | Find properties, classes and codelists whose name, label or definition contains the words given. |
validate_record | Check a record against DCAT-AP-UK (and any extensions). Returns errors, warnings, the conformance level and the quality score. |
convert_mem | Convert a record in the xGov Metadata Exchange Model form to DCAT-AP-UK, listing what changed, and check it. |
convert_openapi | Draft a DCAT-AP-UK data service record from an OpenAPI description (parsed JSON). Email addresses are never copied. |
export_record | Export a record as Turtle, schema.org JSON-LD or Croissant 1.1 (dataset level). |