get_plan_details
AI agents call get_plan_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.
The tool retrieves pension plan details without modifying data. The 'get' prefix and sibling patterns confirm Read category. Severity is medium rather than low because pension plan details may contain sensitive financial/personal information that could be misused if exposed to unauthorized agents, but the tool itself performs no destructive or financial operations.
From the tool's definition Tool name 'get_plan_details' with 'get' prefix indicates data retrieval. No description provided, but context from sibling tools (get_client_details, get_employee_stats, get_help_article, get_notes) establishes a pattern of read-only information retrieval on…
Attacks that exploit this kind of access
get_plan_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_plan_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_plan_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_plan_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_plan_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_plan_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 →