Skip to main content
Glama
Social Fetch MCP

Social Fetch MCP

Official

Search Hugging Face kernels

hugging_face_kernels_search
Read-onlyIdempotent

Search Hugging Face compute kernels by query or author and paginate results to find relevant kernels for model or compute tasks.

Instructions

Search Hugging Face compute kernels. Optional inputs: query, author, limit and cursor. 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_kernels_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoItems per page, 1-1000. A page can hold fewer. Default: 100.
queryNoOnly kernels whose id contains this text.
authorNoOnly kernels owned by this account.
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.
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

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is fully covered elsewhere. The description adds only a light pagination hint ("use cursor when paginated") and says nothing about result shape, cost, or the analytics/conversation plumbing the schema requires.

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 tight sentences with the purpose front-loaded and no filler. The second sentence is slightly redundant in presenting the parameter list as a flat enumeration rather than explaining what the search actually matches.

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

Completeness3/5

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

For a 7-parameter tool with no output schema, the description is thin: it never mentions the required context and llm_model parameters, nor the conversation_id echo rule, all of which gate a successful call. The schema documents them thoroughly, so an agent that reads the schema is fine, but the description alone would leave gaps.

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

Parameters3/5

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

Schema description coverage is 100%, so the baseline is 3. The description's parameter sentence merely restates which four inputs are optional (query, author, limit, cursor) and adds no filtering semantics such as substring matching on kernel id or owner-account scoping beyond what the schema already says.

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

Purpose4/5

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

States a specific verb ("Search") and resource ("Hugging Face compute kernels"), which cleanly separates it from read-oriented siblings such as hugging_face_kernels_get. It does not, however, explain how it differs from other search entry points like hugging_face_search_global or hugging_face_search_fulltext.

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

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance beyond listing which inputs are optional. An agent facing several search-ish siblings (global, fulltext, models, datasets) gets no signal about which one to pick for a kernel lookup.

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