Search logged trades by term (e.g., ticker, direction).
AI agents call search_trades to retrieve information from Trading Analysis MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search/query operation on logged trades, returning results based on search criteria like ticker or direction. It has no side effects, does not execute external operations, does not modify or delete data, and does not involve financial transactions. The blast radius of misuse is minimal—an agent could only retrieve unwanted information already in the system.
From the tool's definition Tool name 'search_trades' and description 'Search logged trades by term' indicate a query operation that retrieves or filters existing trade data without modification or deletion.
Attacks that exploit this kind of access
Search logged trades by term (e.g., ticker, direction). It is categorised as a Read tool in the Trading Analysis MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Trading Analysis MCP Server MCP server in PolicyLayer and add a rule for search_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 Trading Analysis MCP Server. Nothing to install.
search_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 search_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 search_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.
search_trades is provided by the Trading Analysis MCP Server MCP server (zkyko/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 →