AI agents call get_active_account to retrieve information from Schwab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves account metadata (hash and details) without creating, modifying, deleting, executing code, or moving money. It is purely a query operation to fetch the current account state. Even in a financial brokerage context, retrieving account details carries only informational risk (potential data leakage) rather than transactional risk.
From the tool's definition Tool name 'get_active_account' with description 'Return the currently active account hash and its details' indicates retrieval of account information without modification.
Attacks that exploit this kind of access
Return the currently active account hash and its details. It is categorised as a Read tool in the Schwab MCP Server, which means it retrieves data without modifying state.
Register the Schwab MCP server in PolicyLayer and add a rule for get_active_account: 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 Schwab. Nothing to install.
get_active_account 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_active_account 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_active_account. 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_active_account is provided by the Schwab MCP server (k1xme/schwab-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 →