Full-text grep across the Helm
AI agents call kubesearch_grep_values to retrieve information from Kubesearch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs full-text search (grep) across Helm values, which is a read-only operation that retrieves data without modifying, executing, or deleting anything. The blast radius of misuse is minimal—an attacker could enumerate sensitive values in Helm manifests but cannot modify or execute code. Low severity because the scope is limited to searching existing configuration data.
From the tool's definition Tool name 'kubesearch_grep_values' and description 'Full-text grep across the Helm' indicate search/query operations. Grep is a read-only text search utility with no side effects.
Attacks that exploit this kind of access
Full-text grep across the Helm. It is categorised as a Read tool in the Kubesearch MCP Server, which means it retrieves data without modifying state.
Register the Kubesearch MCP server in PolicyLayer and add a rule for kubesearch_grep_values: 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 Kubesearch. Nothing to install.
kubesearch_grep_values 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 kubesearch_grep_values 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 kubesearch_grep_values. 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.
kubesearch_grep_values is provided by the Kubesearch MCP server (perfectra1n/kubesearch-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 →