blv_list_datasets
AI agents call blv_list_datasets to retrieve information from Pypi:swiss Food Safety without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to list available datasets from the BLV (Swiss Federal Food Safety and Veterinary Office) open data source. Listing datasets is a read-only query operation with no ability to modify, delete, or execute code. Even if an AI agent calls this tool, the worst outcome is retrieving information about available datasets.
From the tool's definition Tool name 'blv_list_datasets' indicates a listing/enumeration operation. The description is empty, but the name and context (sibling tools all perform read-only queries on Swiss Federal Food Safety open data) strongly suggest data retrieval without side…
Attacks that exploit this kind of access
blv_list_datasets. It is categorised as a Read tool in the Pypi:swiss Food Safety MCP Server, which means it retrieves data without modifying state.
Register the Pypi:swiss Food Safety MCP server in PolicyLayer and add a rule for blv_list_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 Pypi:swiss Food Safety. Nothing to install.
blv_list_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 blv_list_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 blv_list_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.
blv_list_datasets is provided by the Pypi:swiss Food Safety MCP server (pypi:swiss-food-safety-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 →