Fetch cube CSV export and return parsed rows
AI agents call get_cube_csv_export to retrieve information from CubeCobra MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and formats existing cube data in CSV format. It performs a read-only query operation with no side effects, data modification, or destructive capability. The verb 'Fetch' combined with 'return parsed rows' confirms data retrieval only. Low severity because misuse would only expose data that is likely already publicly accessible through the CubeCobra API.
From the tool's definition Tool name 'get_cube_csv_export' indicates a fetch operation; description 'Fetch cube CSV export and return parsed rows' explicitly uses 'Fetch' and describes data retrieval with parsing, no modification or deletion.
Attacks that exploit this kind of access
Fetch cube CSV export and return parsed rows. It is categorised as a Read tool in the CubeCobra MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CubeCobra MCP Server MCP server in PolicyLayer and add a rule for get_cube_csv_export: 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 CubeCobra MCP Server. Nothing to install.
get_cube_csv_export 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_cube_csv_export 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_cube_csv_export. 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_cube_csv_export is provided by the CubeCobra MCP Server MCP server (plrdev/cubecobra-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 →