AI agents call get_stock_trades to retrieve information from Alpaca without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the tool name and context strongly indicate a read-only query operation. The 'get_' prefix is a standard convention for retrieval without mutation. While the server enables financial operations, this specific tool appears designed to retrieve/list trade information rather than execute trades or modify positions.
From the tool's definition Tool name 'get_stock_trades' indicates data retrieval with no modification. Description is empty, but the naming convention and server context (trading portfolio management) suggest this queries historical or current trade data without side effects.
Attacks that exploit this kind of access
get_stock_trades. It is categorised as a Read tool in the Alpaca MCP Server, which means it retrieves data without modifying state.
Register the Alpaca MCP server in PolicyLayer and add a rule for get_stock_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 Alpaca. Nothing to install.
get_stock_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 get_stock_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 get_stock_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.
get_stock_trades is provided by the Alpaca MCP server (mfoster5303-1/alpaca-mcp-server). 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 →