blv_get_dataset_info
AI agents call blv_get_dataset_info 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 be a metadata/discovery function that retrieves information about datasets (likely descriptions, schemas, or availability). There are no side effects, no data modification, no code execution, and no destructive operations. It is a read-only query operation.
From the tool's definition Tool name 'blv_get_dataset_info' uses the verb 'get', which indicates data retrieval. The description is empty, but the tool name and the server context (queries about food safety, animal disease surveillance, food control results) suggest this retrieves…
Attacks that exploit this kind of access
blv_get_dataset_info. 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_get_dataset_info: 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_get_dataset_info 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_get_dataset_info 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_get_dataset_info. 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_get_dataset_info 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 →