AI agents call get_crypto_bars 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.
The tool retrieves cryptocurrency market data (bars/candlesticks) without side effects. While the server handles financial instruments, this specific tool is a read-only query operation. It does not execute trades, cancel orders, close positions, or modify any account state. Severity is low because misuse only exposes data retrieval, not financial transactions or destructive operations.
From the tool's definition Tool name 'get_crypto_bars' indicates data retrieval of cryptocurrency price/market data (OHLC bars). No description provided, but naming pattern and server context (Alpaca Trading API) confirm it retrieves historical or current market data without…
Attacks that exploit this kind of access
get_crypto_bars. 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_crypto_bars: 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_crypto_bars 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_crypto_bars 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_crypto_bars. 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_crypto_bars 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 →