AI agents call vtk_get_class_info 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.
This tool purely retrieves and queries metadata about VTK classes. It returns informational data (module path, description, methods) without creating, modifying, executing, or destroying anything. This is a standard Read operation—a lookup/fetch function with no side effects or blast radius if misused.
From the tool's definition Tool name 'vtk_get_class_info' and description 'Get complete information about a VTK class including module path, description, and methods' indicate retrieval of class metadata. No side effects, no state modification, no code execution, no data deletion.
Attacks that exploit this kind of access
Get complete information about a VTK class including module path, description, and methods. 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_info: 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_info 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_info 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_info. 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_info 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 →