apibase

Search ML Models

hf.hub.models

Read-onlyIdempotent

Search 1M+ ML models on HuggingFace Hub by name, task (text-generation, image-classification, translation), or library (transformers, diffusers). Returns model ID, downloads, likes, pipeline tag. Sorted by downloads.

Input Schema

TableJSON Schema

Name	Required	Description
`task`	No	Filter by ML task: text-generation, image-classification, translation, text-to-image, automatic-speech-recognition, etc.
`limit`	No	Number of results (1-20, default 10)
`search`	Yes	Search query — model name or keyword (e.g. "llama", "stable-diffusion", "whisper")
`library`	No	Filter by framework: transformers, diffusers, sentence-transformers, gguf, etc.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`error`	No	Present only when the call failed. Includes error code, message, request_id, and any provider-specific extras.
`result`	No	Tool response payload. Shape varies per tool — consult the tool description and inputSchema. May be an object, array, string, or number depending on the upstream provider response.

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 22, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already provide read-only, non-destructive, idempotent, open-world hints. Description adds return fields and sorting, but no mention of pagination defaults. Adds modest value beyond annotations.

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

Conciseness5/5

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

Two concise sentences, front-loaded with key info (search, filters, returns, sorting). No wasted words.

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?

Covers purpose, filters, return fields, and sorting. Lacks mention of default limit or pagination, but output schema likely handles return structure. Good overall.

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?

Input schema has 100% parameter coverage. Description adds context about 1M+ models and sorting by downloads, but schema already explains parameters adequately.

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 clearly states the tool searches ML models on HuggingFace Hub, specifies filters (name, task, library), and lists return fields. It distinguishes from sibling tools like hf.hub.datasets and hf.hub.model_details.

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?

Implies usage for searching models by name/task/library, but no explicit guidance on when to use this vs alternatives or when not to use it.

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

All apibase tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.