AI agents call search-models to retrieve information from Hugging Face MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search query against the Hugging Face Hub's public model repository, returning matching results. It has no side effects, cannot modify data, and poses minimal security risk even if misused by an AI agent—the worst outcome would be unwanted API calls or information gathering about available models.
From the tool's definition Tool name 'search-models' and description 'Search for models on Hugging Face Hub' indicate a query operation that retrieves data without modification. The server is explicitly described as providing 'read-only access' to Hugging Face Hub APIs.
Documented attack patterns abuse exactly the kind of access search-models gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Hugging Face MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search-models:
{
"version": "1",
"default": "deny",
"tools": {
"search-models": {}
}
}search-models is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for models on Hugging Face Hub. It is categorised as a Read tool in the Hugging Face MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Hugging Face MCP Server MCP server in PolicyLayer and add a rule for search-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 Hugging Face MCP Server. Nothing to install.
search-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 search-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 search-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.
search-models is provided by the Hugging Face MCP Server MCP server (shreyaskarnik/huggingface-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 10 Hugging Face MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
10 Hugging Face MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.