Get Terragrunt CLI command help (terragrunt run-all, plan, apply, init, validate, etc.) or list commands by category.
AI agents call cli_reference to retrieve information from Terragrunt MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and returns documentation about Terragrunt CLI commands. It does not execute any commands, modify data, or trigger any external operations. It is a read-only reference lookup with no side effects.
From the tool's definition 'Get Terragrunt CLI command help' and 'list commands by category' — purely retrieves documentation/reference information about CLI commands
Attacks that exploit this kind of access
Get Terragrunt CLI command help (terragrunt run-all, plan, apply, init, validate, etc.) or list commands by category. It is categorised as a Read tool in the Terragrunt MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Terragrunt MCP Server MCP server in PolicyLayer and add a rule for cli_reference: 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 Terragrunt MCP Server. Nothing to install.
cli_reference 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 cli_reference 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 cli_reference. 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.
cli_reference is provided by the Terragrunt MCP Server MCP server (omattsson/terragrunt-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 →