get_client_details
AI agents call get_client_details to retrieve information from PensionPro without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pension administration system where 'client details' likely includes sensitive personal financial information (account balances, beneficiaries, contribution history, retirement projections, SSN/tax ID). While the operation itself is non-destructive read-only access, the sensitivity of pension client data in a financial context elevates the severity.
From the tool's definition Tool name is 'get_client_details' which follows the 'get_' pattern indicating data retrieval. No description provided, but naming convention and sibling tools (get_api_endpoint, get_api_schema, get_employee_stats, get_help_article, get_notes) all establish a…
Attacks that exploit this kind of access
get_client_details. It is categorised as a Read tool in the PensionPro MCP Server, which means it retrieves data without modifying state.
Register the PensionPro MCP server in PolicyLayer and add a rule for get_client_details: 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 PensionPro. Nothing to install.
get_client_details 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_client_details 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_client_details. 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_client_details is provided by the PensionPro MCP server (pypi:pension-pro-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 →