List all variables for a dataset in an ERDDAP server
AI agents call list_dataset_variables to retrieve information from Erddap Mcp Demo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists metadata (variable information) from an ERDDAP oceanographic data server. It is a read-only operation with no ability to modify, execute external code, delete data, or initiate financial transactions.
From the tool's definition Tool name 'list_dataset_variables' and description 'List all variables for a dataset in an ERDDAP server' indicate a retrieval/query operation that returns metadata about dataset variables with no side effects.
Attacks that exploit this kind of access
List all variables for a dataset in an ERDDAP server. It is categorised as a Read tool in the Erddap Mcp Demo MCP Server, which means it retrieves data without modifying state.
Register the Erddap Mcp Demo MCP server in PolicyLayer and add a rule for list_dataset_variables: 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 Erddap Mcp Demo. Nothing to install.
list_dataset_variables 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 list_dataset_variables 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 list_dataset_variables. 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.
list_dataset_variables is provided by the Erddap Mcp Demo MCP server (srstsavage/erddap-mcp-demo). 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 →