Get the holdings of a brokerage account.
AI agents call get_account_holdings to retrieve information from Composer Trade without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves account data (holdings) without modifying, deleting, or executing any trades or financial transactions. While the server overall enables trading (Financial category tools exist), this specific tool is a pure read operation that queries existing portfolio data. The blast radius of misuse is limited to information disclosure.
From the tool's definition Tool name is 'get_account_holdings' and description states 'Get the holdings of a brokerage account.' The verb 'Get' and the read-only nature of retrieving account holdings information indicate a query operation with no side effects.
Attacks that exploit this kind of access
Get the holdings of a brokerage account. It is categorised as a Read tool in the Composer Trade MCP Server, which means it retrieves data without modifying state.
Register the Composer Trade MCP server in PolicyLayer and add a rule for get_account_holdings: 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 Composer Trade. Nothing to install.
get_account_holdings 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_account_holdings 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_account_holdings. 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_account_holdings is provided by the Composer Trade MCP server (tanwithme/composer-trade-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 →