AI agents call query_climate 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.
Based on context from the server description and naming conventions, this tool appears to retrieve historical climate/meteorological data without modifying it. The 'query' action on read-only climate datasets is a Read operation. Empty tool description prevents higher confidence, but the pattern matches other retrieval-focused tools on this server (geocode, get_coverage, water_risk).
From the tool's definition Tool name 'query_climate' and server description indicating access to 'historical air quality, ERA5 meteorology' data; the 'query_' prefix and sibling tools like 'query_climate_point' suggest data retrieval operations.
Attacks that exploit this kind of access
query_climate. 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 query_climate: 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.
query_climate 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 query_climate 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 query_climate. 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.
query_climate 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 →