AI agents call estimate_query_cost 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.
The name indicates a read-only operation that queries or estimates costs without side effects. The lack of description lowers confidence, but the semantic meaning of 'estimate' and 'query_cost' strongly suggests retrieval rather than modification, execution, or deletion. Classified as Read with low severity due to the benign nature of cost estimation queries.
From the tool's definition Tool name 'estimate_query_cost' suggests it calculates or retrieves cost information without modifying data. No description provided to confirm behavior.
Attacks that exploit this kind of access
estimate_query_cost. 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 estimate_query_cost: 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.
estimate_query_cost 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 estimate_query_cost 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 estimate_query_cost. 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.
estimate_query_cost 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 →