AI agents call vtk_get_class_action_phrase to retrieve information from Vtkapi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool simply fetches and returns descriptive information about VTK class behavior without modifying, executing, or deleting anything. It is a pure data retrieval operation analogous to documentation lookup or API introspection, which poses minimal security risk in isolation.
From the tool's definition Tool name 'vtk_get_class_action_phrase' and description indicate it retrieves metadata (action phrase descriptions) about VTK classes. This is a query/lookup operation with no side effects.
Attacks that exploit this kind of access
Get the action phrase describing what a VTK class does (e.g.,. It is categorised as a Read tool in the Vtkapi MCP Server, which means it retrieves data without modifying state.
Register the Vtkapi MCP server in PolicyLayer and add a rule for vtk_get_class_action_phrase: 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 Vtkapi. Nothing to install.
vtk_get_class_action_phrase 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 vtk_get_class_action_phrase 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 vtk_get_class_action_phrase. 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.
vtk_get_class_action_phrase is provided by the Vtkapi MCP server (patrickoleary/vtkapi-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 →