AI agents call get_coverage to retrieve information from Jiskta without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the tool name 'get_coverage' and its placement among data-querying tools (query_climate, find_facilities, geocode, etc.) strongly suggest it queries or retrieves metadata about data availability rather than modifying or executing operations. The lack of descriptive text reduces confidence from high to moderate, but the name pattern aligns with informational read operations.
From the tool's definition Tool name 'get_coverage' with empty description; likely retrieves coverage information for available data (air quality, meteorology, water risk, geocoding, facilities) based on server context.
Attacks that exploit this kind of access
get_coverage. It is categorised as a Read tool in the Jiskta MCP Server, which means it retrieves data without modifying state.
Register the Jiskta MCP server in PolicyLayer and add a rule for get_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 Jiskta. Nothing to install.
get_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 get_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 get_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.
get_coverage is provided by the Jiskta MCP server (jiskta/jiskta-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 →