Fetch the history of closed trades.
AI agents call fetch_trades to retrieve information from Freqtrade-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical trade data from the Freqtrade bot. It performs a query-like operation with no ability to modify, delete, or execute trades. Even in the context of a trading bot, fetching historical data is a read-only operation. The blast radius if misused by an AI agent is minimal—it only exposes past trade records, not the ability to place new trades or modify configuration.
From the tool's definition Tool name is 'fetch_trades' and description states 'Fetch the history of closed trades' — both indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Fetch the history of closed trades. It is categorised as a Read tool in the Freqtrade-MCP MCP Server, which means it retrieves data without modifying state.
Register the Freqtrade- MCP server in PolicyLayer and add a rule for fetch_trades: 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 Freqtrade-MCP. Nothing to install.
fetch_trades 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 fetch_trades 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 fetch_trades. 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.
fetch_trades is provided by the Freqtrade- MCP server (worlddebugger/freqtrade-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 →