Dataset licence facts
Licence facts for popular Hugging Face datasets: declared licence, files, sources, conflicts.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"dataset-licence": {
"url": "https://mcp.datalicense.uk/mcp"
}
}
}遠端端點
https://mcp.datalicense.uk/mcpstreamable-http它能做什麼
工具清單
工具（2）
🟢dataset_licence(id, live)
Retrieve licence facts for one Hugging Face dataset: declared licence, where it was declared, recorded source datasets, detected licence files and a signal. Each licence value comes with an evidence URL linking to the Hub file, API record, file list or Hub page that was checked, with a commit-specific link where available. For datasets in the daily build, facts come from the build by default. Other public datasets are checked live on the Hugging Face Hub. 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.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Dataset ID, for example 'owner/name'."
},
"live": {
"type": "boolean",
"description": "Check the Hub now instead of using the facts published by the daily build. Datasets not in the build are always checked live."
}
},
"required": [
"id"
],
"additionalProperties": false
}🟢find_datasets(signal, task, licence, limit)
Search the 5,000 most downloaded Hugging Face datasets in the daily build, returning matches in descending order of download count. Optionally filter by signal, task tag and declared licence ID; all supplied filters must match. Returns up to 50 results; licence_evidence links to the Hub file, API record or file list checked for a declared licence. 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.
輸入結構描述
{
"type": "object",
"properties": {
"signal": {
"type": "string",
"enum": [
"permissive",
"restrictive",
"conflict",
"unclear"
],
"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."
},
"task": {
"type": "string",
"description": "Task tag, for example 'text-generation'."
},
"licence": {
"type": "string",
"description": "Declared licence ID, for example 'apache-2.0'."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Default 20, maximum 50."
}
},
"additionalProperties": false
}社群
證據