AI agents call vtk_search_classes 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 is a search/query operation that retrieves information about VTK classes from the API documentation. It has no capability to modify, execute, delete, or create data. The context of the server (validating VTK Python code by checking class existence) confirms this is an informational lookup tool with no side effects.
From the tool's definition Tool description states it 'Search[es] for VTK classes by name or keyword' and server purpose is validation/checking of VTK API without modification. No side effects, data creation, code execution, deletion, or financial operations are indicated.
Attacks that exploit this kind of access
Search for VTK classes by name or keyword. 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_search_classes: 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_search_classes 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_search_classes 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_search_classes. 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_search_classes 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 →