Search through Kubernetes runbooks by keyword
AI agents call search-runbooks to retrieve information from Kubernetes Runbooks without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information (runbooks/guides) based on search parameters. It has no side effects: it does not create, modify, delete, or execute any actions. The worst-case misuse scenario is an AI agent retrieving irrelevant or misleading documentation, which has minimal blast radius. Classification as Read is appropriate.
From the tool's definition Tool performs 'search through Kubernetes runbooks by keyword' — a query operation that retrieves documentation without modifying, executing, or deleting data.
Attacks that exploit this kind of access
Search through Kubernetes runbooks by keyword. It is categorised as a Read tool in the Kubernetes Runbooks MCP Server, which means it retrieves data without modifying state.
Register the Kubernetes Runbooks MCP server in PolicyLayer and add a rule for search-runbooks: 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 Kubernetes Runbooks. Nothing to install.
search-runbooks 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 search-runbooks 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 search-runbooks. 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.
search-runbooks is provided by the Kubernetes Runbooks MCP server (raihan0824/kubernetes-runbooks-mcp-server). 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 →