Retrieves structural metadata for a specific datacube (coverage).
AI agents call describe_coverage to retrieve information from Rasdaman MCP Server 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 operation that queries and returns metadata about a coverage object. There are no side effects, no data modification, no code execution, and no destructive operations. The blast radius is minimal - the worst outcome is exposure of datacube structure information, which is typically non-sensitive metadata. Confidence is high because the description is clear and unambiguous.
From the tool's definition Tool retrieves structural metadata for a specific datacube (coverage). The description uses 'Retrieves' and 'metadata', indicating data query without modification or execution of arbitrary operations.
Documented attack patterns abuse exactly the kind of access describe_coverage gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Rasdaman MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for describe_coverage:
{
"version": "1",
"default": "deny",
"tools": {
"describe_coverage": {}
}
}describe_coverage is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retrieves structural metadata for a specific datacube (coverage). It is categorised as a Read tool in the Rasdaman MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Rasdaman MCP Server MCP server in PolicyLayer and add a rule for describe_coverage: 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 Rasdaman MCP Server. Nothing to install.
describe_coverage 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 describe_coverage 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 describe_coverage. 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.
describe_coverage is provided by the Rasdaman MCP Server MCP server (rasdaman/rasdaman-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Rasdaman MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Rasdaman MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.