hf.hub.models
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.
This record as markdown: /tools/io-github-whiteknightonhorse-apibase/hf.hub.models.md
What hf.hub.models does on Apibase
AI agents call hf.hub.models to retrieve information from Apibase without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
task | string | — | Filter by ML task: text-generation, image-classification, translation, text-to-image, automatic-speech-recognition, etc. |
limit | integer | — | Number of results (1-20, default 10) |
search | string | Yes | Search query — model name or keyword (e.g. "llama", "stable-diffusion", "whisper") |
library | string | — | Filter by framework: transformers, diffusers, sentence-transformers, gguf, etc. |
Parameters from the server's own tool schema.
Why hf.hub.models is rated Low
Tool retrieves public model metadata from HuggingFace Hub without side effects or data modification.
From the tool's definition Search 1M+ ML models, returns model ID, downloads, likes, pipeline tag.
Attacks that exploit this kind of access
The rule that runs hf.hub.models safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Apibase, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For hf.hub.models, this is the rule to start with:
hf.hub.models is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Apibase, apply this rule, and every hf.hub.models call is checked against it from then on.
Questions about hf.hub.models
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. It is categorised as a Read tool in the Apibase MCP Server, which means it retrieves data without modifying state.
hf.hub.models accepts 4 parameters: task, limit, search, library. Required: search. The full parameter table on this page comes from the server's own tool schema.
Register the Apibase MCP server in PolicyLayer and add a rule for hf.hub.models: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Apibase. Nothing to install.
hf.hub.models is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the hf.hub.models rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for hf.hub.models. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
hf.hub.models is provided by the Apibase MCP server (apibase-mcp-client). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Apibase, and thousands of servers like it.
This server
Across the catalogue