huggingface_search_datasets
AI agents call huggingface_search_datasets to retrieve information from Integrations MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'search' operation is fundamentally a retrieval function that queries available datasets on HuggingFace without side effects. No data creation, modification, deletion, or execution occurs. While the description is empty, the name structure and context of sibling tools (airtable_create_record, airtable_delete_record, airtable_update_record) confirm this is a read operation following standard naming conventions.
From the tool's definition Tool name contains 'search' which is a read operation that queries and retrieves data. The tool name 'huggingface_search_datasets' indicates it searches for datasets without modifying them.
Attacks that exploit this kind of access
huggingface_search_datasets. It is categorised as a Read tool in the Integrations MCP MCP Server, which means it retrieves data without modifying state.
Register the Integrations MCP server in PolicyLayer and add a rule for huggingface_search_datasets: 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 Integrations MCP. Nothing to install.
huggingface_search_datasets 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 huggingface_search_datasets 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 huggingface_search_datasets. 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.
huggingface_search_datasets is provided by the Integrations MCP server (shriram-vasudevan/integrations-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 →