Fetch board-labeled plaintext export
AI agents call get_cube_plaintext 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 exports cube data in plaintext format. It performs no modification, deletion, or execution of external systems. The 'Fetch' action is a straightforward query operation that returns data without altering any state. This is consistent with other sibling tools like 'get_cube_csv_export', 'get_cube_json', and 'get_cube_list', which are all Read category tools.
From the tool's definition Tool name 'get_cube_plaintext' and description 'Fetch board-labeled plaintext export' indicate a retrieval operation. The verb 'Fetch' and the read-only nature of exporting data in plaintext format confirm this is a data retrieval action with no side effects.
Attacks that exploit this kind of access
Fetch board-labeled plaintext export. 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_plaintext: 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_plaintext 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_plaintext 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_plaintext. 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_plaintext 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.
get_cube_plaintext is one line of CubeCobra MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →