AI agents call trades_history to retrieve information from Kraken Pro MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although the description is empty (lowering confidence to 0.7), the tool name and context of a financial trading platform indicate this retrieves historical trade records. This is a Read operation—it queries financial data but does not execute trades, move money, or modify account state.
From the tool's definition Tool name 'trades_history' indicates retrieval of historical trade data with no modification capability. Sibling tools like 'add_order', 'amend_order', and 'cancel_order' are Write/Execute; this tool lacks those action verbs, suggesting it queries data only.
Documented attack patterns abuse exactly the kind of access trades_history gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kraken Pro MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for trades_history:
{
"version": "1",
"default": "deny",
"tools": {
"trades_history": {}
}
}trades_history is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
trades_history. It is categorised as a Read tool in the Kraken Pro MCP MCP Server, which means it retrieves data without modifying state.
Register the Kraken Pro MCP server in PolicyLayer and add a rule for trades_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 Kraken Pro MCP. Nothing to install.
trades_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 trades_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 trades_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.
trades_history is provided by the Kraken Pro MCP server (oilst/kraken-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kraken Pro MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
17 Kraken Pro MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.