AI agents call get_dataset_metadata to retrieve information from Mcp Csu without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query operation that returns informational metadata about datasets without altering data, executing code, or producing side effects. The blast radius of misuse is minimal—an AI agent could at worst retrieve metadata it shouldn't know, but cannot modify, delete, or execute operations. Classified as Read with low severity.
From the tool's definition Tool retrieves metadata (record count, time range, last update) about dataset content with no modification or execution capability.
Attacks that exploit this kind of access
Get metadata about dataset content: record count, time range, last update. It is categorised as a Read tool in the Mcp Csu MCP Server, which means it retrieves data without modifying state.
Register the Mcp Csu MCP server in PolicyLayer and add a rule for get_dataset_metadata: 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 Mcp Csu. Nothing to install.
get_dataset_metadata 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 get_dataset_metadata 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 get_dataset_metadata. 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.
get_dataset_metadata is provided by the Mcp Csu MCP server (reloadcz/mcp-csu). 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 →