AI agents call vtk_get_class_doc 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 performs a read-only operation—retrieving documentation metadata about VTK classes. It has no side effects, cannot modify data, execute arbitrary code, or trigger external operations. The worst-case misuse by an AI agent would be wasting compute retrieving excessive documentation, presenting minimal risk.
From the tool's definition Tool name 'vtk_get_class_doc' and description 'Get the class documentation string for a VTK class' indicate a retrieval operation that queries and returns documentation without modifying any data or executing code.
Attacks that exploit this kind of access
Get the class documentation string for a VTK class. 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_doc: 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_doc 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_doc 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_doc. 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_doc 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 →