Get the Croissant metadata for a dataset. Croissant is a high-level format for machine learning datasets.
AI agents call hf_get_croissant to retrieve information from Hugging Face Hub MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about datasets in Croissant format. It performs a read-only query operation with no side effects, no data modification, no code execution, and no destructive capability. The blast radius of misuse is minimal—an agent could only access publicly available metadata about datasets. There is no financial impact, no code execution capability, and no way to modify or delete data.
From the tool's definition Tool name and description indicate retrieval of metadata: 'Get the Croissant metadata for a dataset' with no modification, deletion, or code execution. Part of a suite of retrieval tools (hf_get_*, hf_list_*) that query the Hugging Face Hub API.
Attacks that exploit this kind of access
Get the Croissant metadata for a dataset. Croissant is a high-level format for machine learning datasets. It is categorised as a Read tool in the Hugging Face Hub MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Hugging Face Hub MCP Server MCP server in PolicyLayer and add a rule for hf_get_croissant: 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 Hub MCP Server. Nothing to install.
hf_get_croissant 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_get_croissant 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_get_croissant. 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_get_croissant is provided by the Hugging Face Hub MCP Server MCP server (michaelwaves/hf-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →