get_container_llm_analysis
Analyze container process trees using LLM to identify security risks in Kubernetes environments.
Instructions
Get LLM analysis of a container's process tree
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| container_id | Yes | Container ID to get LLM analysis for |
Implementation Reference
- src/operations/runtime.ts:13-15 (schema)Zod schema defining the input parameters for the get_container_llm_analysis tool: container_id (string).export const GetContainerLLMAnalysisSchema = z.object({ container_id: z.string().describe("Container ID to get LLM analysis for"), });
- src/operations/runtime.ts:168-178 (handler)Handler function that fetches container runtime insights for the given container_id and returns the LLM analysis from the first entry.export async function getContainerLLMAnalysis( client: RadSecurityClient, containerId: string ): Promise<any> { const cris = await client.makeRequest( `/accounts/${client.getAccountId()}/container_runtime_insights`, { container_id: containerId } ); return cris.entries[0].analysis; }
- src/index.ts:376-381 (registration)Tool registration in the listTools response, defining the tool name, description, and input schema.name: "get_container_llm_analysis", description: "Get LLM analysis of a container's process tree", inputSchema: zodToJsonSchema( runtime.GetContainerLLMAnalysisSchema ), },
- src/index.ts:1164-1177 (registration)Handler registration in the callTool switch case, parsing args with schema and calling the handler function.case "get_container_llm_analysis": { const args = runtime.GetContainerLLMAnalysisSchema.parse( request.params.arguments ); const response = await runtime.getContainerLLMAnalysis( client, args.container_id ); return { content: [ { type: "text", text: JSON.stringify(response, null, 2) }, ], }; }