AI agents call vtk_get_method_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 is a read-only query operation that retrieves metadata (docstrings) about VTK API methods. It has no side effects, cannot modify or delete data, and cannot execute code. The worst-case misuse would be an AI agent getting incorrect or misleading documentation, but this is a data retrieval function with minimal blast radius.
From the tool's definition Tool retrieves documentation ('Get just the docstring') for VTK class methods. No modification, deletion, or execution of code occurs—it only queries and returns existing API documentation.
Attacks that exploit this kind of access
Get just the docstring for a specific method of 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_method_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_method_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_method_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_method_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_method_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 →