Retrieve the binary content of a completed export by id.
AI agents call retrieve_export to retrieve information from Mcp Kraken without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches previously generated export data by identifier. It does not create, modify, delete, or execute operations—it simply reads and returns existing binary content. While the Kraken context involves financial data, the tool itself performs no financial transaction or money movement.
From the tool's definition Tool name 'retrieve_export' and description 'Retrieve the binary content of a completed export by id' indicate data retrieval with no modification. The verb 'retrieve' and the passive object 'completed export' confirm this is a read-only query operation.
Attacks that exploit this kind of access
Retrieve the binary content of a completed export by id. It is categorised as a Read tool in the Mcp Kraken MCP Server, which means it retrieves data without modifying state.
Register the Mcp Kraken MCP server in PolicyLayer and add a rule for retrieve_export: 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 Mcp Kraken. Nothing to install.
retrieve_export 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 retrieve_export 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 retrieve_export. 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.
retrieve_export is provided by the Mcp Kraken MCP server (xavierbeheydt/mcp-kraken). 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 →