search_plans
AI agents call search_plans 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 name strongly implies data retrieval from the PensionPro system. With no description contradicting this, and given the context of a pension administration API where searching plans would typically be a read-only query operation, this is classified as Read. Severity is low because search operations generally have limited blast radius—they retrieve existing data without side effects. Confidence is moderate (0.
From the tool's definition Tool name 'search_plans' indicates a search/query operation returning pension plan data; no description provided to suggest modification or deletion capabilities.
Attacks that exploit this kind of access
search_plans. 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 search_plans: 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.
search_plans 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 search_plans 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 search_plans. 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.
search_plans 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 →