get_worktray
AI agents call get_worktray 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 appears designed to retrieve worktray data from the PensionPro pension administration system. No side effects or modifications are indicated by the name or context. The empty description lowers confidence slightly, but the consistent naming convention with other read operations on this server strongly suggests this is a retrieval operation.
From the tool's definition Tool name 'get_worktray' follows the 'get_' prefix pattern consistent with other read-only tools on this server (get_api_endpoint, get_api_schema, get_client_details, get_employee_stats, get_help_article, get_notes).
Attacks that exploit this kind of access
get_worktray. 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_worktray: 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_worktray 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_worktray 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_worktray. 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_worktray 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 →