Licence facts for popular Hugging Face datasets: declared licence, files, sources, conflicts.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Retrieve published licence facts for one Hugging Face dataset in this site's index: declared licence, where it was declared, recorded source datasets, detected licence files and a signal. Signal values: permissive = permissive or share-alike licence reported; restrictive = use restrictions reported; conflict = possible licence conflict; unclear = insufficient or unrecognised licence information. These signals do not establish permission to use a dataset. Licence facts reported by the dataset and its declared sources. Not legal advice, and not a grant of permission to use the dataset.
Dataset ID, for example 'owner/name'.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http dataset-licence https://mcp.datalicense.uk/mcp
Retrieve published licence facts for one Hugging Face dataset in this site's index: declared licence, where it was declared, recorded source datasets, detected licence files and a signal. Signal values: permissive = permissive or share-alike licence reported; restrictive = use restrictions reported; conflict = possible licence conflict; unclear = insufficient or unrecognised licence information. These signals do not establish permission to use a dataset. Licence facts reported by the dataset and its declared sources. Not legal advice, and not a grant of permission to use the dataset.
| Argument | Type | Description |
|---|---|---|
| id* | string | Dataset ID, for example 'owner/name'. |
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "Dataset ID, for example 'owner/name'."
}
},
"additionalProperties": false
}List popular Hugging Face datasets from the published index, ordered by download count from highest to lowest. Optionally filter by signal, task tag and declared licence ID; all supplied filters must match. Returns up to 50 results. Signal values: permissive = permissive or share-alike licence reported; restrictive = use restrictions reported; conflict = possible licence conflict; unclear = insufficient or unrecognised licence information. These signals do not establish permission to use a dataset. Licence facts reported by the dataset and its declared sources. Not legal advice, and not a grant of permission to use the dataset.
| Argument | Type | Description |
|---|---|---|
| task | string | Task tag, for example 'text-generation'. |
| limit | integer | Default 20, maximum 50. |
| signal | string | Signal values: permissive = permissive or share-alike licence reported; restrictive = use restrictions reported; conflict = possible licence conflict; unclear = insufficient or unrecognised licence information. These signals do not establish permission to use a dataset. |
| licence | string | Declared licence ID, for example 'apache-2.0'. |
{
"type": "object",
"properties": {
"task": {
"type": "string",
"description": "Task tag, for example 'text-generation'."
},
"limit": {
"type": "integer",
"maximum": 50,
"minimum": 1,
"description": "Default 20, maximum 50."
},
"signal": {
"enum": [
"permissive",
"restrictive",
"conflict",
"unclear"
],
"type": "string",
"description": "Signal values: permissive = permissive or share-alike licence reported; restrictive = use restrictions reported; conflict = possible licence conflict; unclear = insufficient or unrecognised licence information. These signals do not establish permission to use a dataset."
},
"licence": {
"type": "string",
"description": "Declared licence ID, for example 'apache-2.0'."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Oct 30, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.