AI agents use create_watchlist to create or update resources in Alpaca — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Alpaca environment.
Creating a watchlist is a non-destructive write operation that adds data to the user's account. While the server provides financial trading tools, this specific tool does not move money, execute trades, or modify positions—it only organizes symbols for monitoring. The severity is low because watchlist creation has minimal blast radius; the worst outcome is organizing unwanted symbols, which can be easily removed.
From the tool's definition Tool name 'create_watchlist' and description 'Creates a new watchlist with specified symbols' indicate a write operation that creates new data (watchlist).
Attacks that exploit this kind of access
Creates a new watchlist with specified symbols. It is categorised as a Write tool in the Alpaca MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Alpaca MCP server in PolicyLayer and add a rule for create_watchlist: 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.
create_watchlist is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_watchlist 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 create_watchlist. 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.
create_watchlist 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 →