get_project_details
AI agents call get_project_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 name 'get_project_details' indicates a read operation that retrieves data. While the description is empty, the naming convention and context of other sibling tools (primarily 'get_*' for reading and 'create_*'/'complete_*'/'add_*' for modifications) strongly suggests this is a query operation. In a pension administration system, retrieving project details is a read-only operation without side effects.
From the tool's definition Tool name 'get_project_details' and sibling tools like 'get_client_details', 'get_employee_stats', 'get_notes', 'get_api_schema' suggest retrieval operations with no side effects.
Attacks that exploit this kind of access
get_project_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_project_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_project_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_project_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_project_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_project_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 →