VALIDATION ONLY: Validates existing vCluster YAML (full config or partial snippet) against the schema. Use create-vcluster-config for configs you generate. Use this to validate user-provided configs or files from GitHub.
AI agents call validate-config to retrieve information from Vcluster Yaml without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only performs schema validation (validation checks against known rules), which is a non-destructive read operation that retrieves/queries data and produces no side effects. It does not create, modify, delete, or execute any infrastructure changes. The explicit "VALIDATION ONLY" statement confirms the read-only nature.
From the tool's definition Tool description explicitly states "VALIDATION ONLY" and performs validation of existing configurations against schema with no capability to create, modify, delete or execute operations. The tool is read-only analysis of user-provided or existing configs.
Attacks that exploit this kind of access
VALIDATION ONLY: Validates existing vCluster YAML (full config or partial snippet) against the schema. Use create-vcluster-config for configs you generate. Use this to validate user-provided configs or files from GitHub. It is categorised as a Read tool in the Vcluster Yaml MCP Server, which means it retrieves data without modifying state.
Register the Vcluster Yaml MCP server in PolicyLayer and add a rule for validate-config: 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 Vcluster Yaml. Nothing to install.
validate-config 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 validate-config 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 validate-config. 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.
validate-config is provided by the Vcluster Yaml MCP server (vcluster-yaml-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 →