Skip to content

Licence facts for popular Hugging Face datasets MCP server

Which MCP servers are Licence facts for popular Hugging Face datasets's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-30

← Back to Licence facts for popular Hugging Face datasets

Whose server it is
  • Registry nameuk.datalicense/dataset-licenceverified in the MCP registry

The registry name sits under datalicense.uk. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-30
  • Stateanswerschecked 2026-10-30
  • Tools2
  • Server calls itselfdataset-licence-mcp
  • Server version0.1.0
  • Protocol version2025-06-18

On 2026-10-30 the server answered initialize and tools/list without a sign-in. First answer in 46 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: look up a Hugging Face dataset's declared licence; compare a dataset's declared and detected licences; spot possible licence conflicts with a dataset's sources.
  • Checked on 3 of the 7 days it takes to judge reliability.

Once connected

  • For "look up a Hugging Face dataset's declared licence", the likely first call is dataset_licence.
  • For "compare a dataset's declared and detected licences", the likely first call is dataset_licence.
  • For "spot possible licence conflicts with a dataset's sources", the likely first call is dataset_licence.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 3, the first on 2026-10-30
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer45 ms
  • Space in an agent's context≈ 689 tokensthe definitions of all its tools (2), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once
  • Not saying whether it only reads or can destroy: 2 of 2

What an agent can do with it

  • can do · look up a Hugging Face dataset's declared licence
  • can do · compare a dataset's declared and detected licences
  • can do · spot possible licence conflicts with a dataset's sources

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers2 tools · read 2026-10-30
  • dataset_licence

    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…

  • find_datasets

    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…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "dataset-licence": {
      "type": "http",
      "url": "https://mcp.datalicense.uk/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http datalicense https://mcp.datalicense.uk/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.datalicense.uk/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.