Skip to main content
Glama
Social Fetch MCP

Social Fetch MCP

Official

Search Hugging Face datasets

hugging_face_datasets_search
Read-onlyIdempotent

Search Hugging Face datasets by keyword, language, license, or tags to find training data for your project. Filter and sort results, then paginate to explore matching datasets.

Instructions

Search and filter Hugging Face datasets by keyword, language, licence and tags. Optional inputs: query, author, language, license, tags and 5 more. Returns a list (use cursor when paginated).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "hugging_face_datasets_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoSort order: `downloads` (last 30 days), `likes`, `likes7d`, `likes30d`, `trending`, `created` or `updated`. Default: `trending`. Datasets sorted by `likes30d` need a `query` or an `author`.
tagsNoComma-separated tags the repository must all have, e.g. `text-classification,pytorch` or `license:mit`.
gatedNo`true` for gated datasets only, `false` to hide them.
limitNoItems per page, 1-1000. A page can hold fewer. Default: 50.
orderNo`desc` (default) or `asc`. `asc` only works with `sort=created`.
queryNoSearch text. Matches repository ids, tags and card text.
authorNoOnly repositories owned by this user or organization.
cursorNoPass `page.nextCursor` from the previous response to get the next page. Keep every other parameter the same.
contextYesDescribe the user's underlying goal in one sentence, not the tool you are calling.
licenseNoLicence id, e.g. `apache-2.0` or `cc-by-4.0`.
languageNoLanguage code tag, e.g. `en`.
llm_modelYesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess.
conversation_idNoEcho the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A3.9/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds that results come back as a list and are cursor-paginated, but it says nothing about rate limits, result caps, or the fact that the response carries a nextCursor the caller must echo. It does not contradict the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two front-loaded sentences with no filler, and the primary purpose leads. The parenthetical 'and 5 more' is a small flaw, since it enumerates some parameters and then gestures at the rest, which gives an agent a partial and slightly misleading inventory when the schema is complete.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 13-parameter search tool with no output schema, the description covers what the tool does, the filter dimensions, the return type and pagination. The gap is that the two required analytics parameters (context, llm_model) and the required conversation_id handshake go unmentioned, though the schema documents them thoroughly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents sort, tags, gated, limit, order, query, author, cursor, license and language in detail with examples and enum meanings. The description only restates a partial facet list including a vague 'and 5 more', so it adds little beyond the schema; nothing is lost, but nothing is gained either.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('Search and filter Hugging Face datasets') plus the facets it operates on, which makes it immediately distinguishable from retrieval siblings like hugging_face_datasets_get or from the models/spaces search tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the verb 'search'; there is no statement of when to prefer this over hugging_face_datasets_get, search_fulltext, or search_global, and no exclusions or prerequisites. The one concrete usage instruction is the pagination hint ('use cursor when paginated'), which is helpful but narrow.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools