get_trade_history
AI agents call get_trade_history 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 queries past trade history—a read-only operation with no side effects on account state or positions. However, severity is elevated to medium because trade history may contain sensitive information (account activity, trading patterns, positions) that could be misused if an agent discloses it or makes decisions based on incomplete/stale data.
From the tool's definition Tool name 'get_trade_history' indicates a retrieval operation returning historical trading data from the Kraken API. No description provided, but naming convention and position among financial trading tools suggests data retrieval only.
Attacks that exploit this kind of access
get_trade_history. 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 get_trade_history: 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.
get_trade_history 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_trade_history 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_trade_history. 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_trade_history 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 →