// SCAN REPORT

Terragrunt GCP Tool MCP

33 tools. 11 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 1 Jul 2026

11 can modify or destroy data

22 read-only

33 tools total

Community server · catalogue entry verified 01/07/2026

How to control Terragrunt GCP Tool MCP ↓

TOOL MAP

What Terragrunt GCP Tool MCP exposes to your agents

Read (22) Write / Execute (8) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Terragrunt GCP Tool MCP tools

Destructive · Critical delete_resource Deletion of infrastructure resources is irreversible and cannot be undone. Destructive · Critical rollback_deployment Rolling back a deployment in GCP infrastructure managed by Terragrunt involves destroying newly created resources and/or restoring previous configurations — operations that are irreversible with potentially broad blast r Execute · High deploy_resources This tool triggers deployment operations on Google Cloud Platform infrastructure. Execute · High execute_stack_command This tool allows execution of commands against GCP infrastructure stacks with parallel processing.

11 of Terragrunt GCP Tool MCP's 33 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Terragrunt GCP Tool MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and Terragrunt GCP Tool MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_resource": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "create_resource": {
    "limits": [
      {
        "counter": "create_resource_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_dependencies": {
    "limits": [
      {
        "counter": "analyze_dependencies_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Terragrunt GCP Tool MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON TERRAGRUNT GCP TOOL →

Instant setup, no code required.

FULL CATALOGUE

All 33 Terragrunt GCP Tool MCP tools

DESTRUCTIVE 2 tools

Destructive delete_resource Delete a resource (with dependency checking) Destructive rollback_deployment Rollback a failed deployment

EXECUTE 3 tools

Execute apply_resource_deployment Apply changes to a Terragrunt resource with safety checks Execute deploy_resources Deploy infrastructure changes (deprecated, use apply_resource_deployment) Execute execute_stack_command Execute commands on stacks with parallel execution and dependency management

WRITE 5 tools

Write create_resource Create a new infrastructure resource Write plan_deployment Generate deployment plan for changes (deprecated, use plan_resource_deployment) Write plan_resource_deployment Generate a comprehensive deployment plan for a Terragrunt resource Write send_slack_notification Send notifications to team Write update_resource Update an existing resource configuration

READ 22 tools

Read analyze_dependencies Analyze resource dependencies Read check_deployment_status Check status of ongoing deployments Read check_drift Detect configuration drift Read create_deployment_summary Generate deployment reports Read draw_resource_tree Draw a visual resource tree using Terragrunt CLI redesign commands Read get_audit_log Retrieve audit logs Read get_autodevops_system_prompt Get system prompts for LLM integration to create AutoDevOps assistants Read get_cost_alerts Cost alerts based on budget thresholds and spending patterns Read get_cost_analysis Get infrastructure cost breakdown Read get_cost_optimization_score Infrastructure cost optimization scoring and recommendations Read get_cost_status Complete cost status dashboard with analysis, alerts, and optimization insights Read get_dependency_graph Generate dependency graphs in DOT, Mermaid, or JSON format Read get_enhanced_infrastructure_status Get comprehensive status including both traditional resources and stacks Read get_infrastructure_status Get overall infrastructure health Read get_resource Get detailed information about a specific resource (deprecated, use get_resource_details) Read get_resource_details Get comprehensive information about a specific resource including attributes, state, and configuration Read get_stack_details Get detailed information about a specific stack including units and execution order Read get_stack_outputs Get aggregated outputs from stack-level operations Read list_resources List all resources in the infrastructure Read list_stacks List all Terragrunt stacks using experimental features Read validate_resource_config Validate a Terragrunt resource configuration with dependency checking Read visualize_infrastructure Comprehensive infrastructure visualization combining trees and graphs

OTHER 1 tools

Other Built in integration guides for Claude Desktop, APIs, and automation tools

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Terragrunt GCP Tool MCP

Can an AI agent delete data through the Terragrunt GCP Tool MCP server? +

Yes. The Terragrunt GCP Tool MCP server exposes 2 destructive tools including delete_resource, rollback_deployment. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Terragrunt GCP Tool MCP? +

The Terragrunt GCP Tool MCP server has 5 write tools including create_resource, plan_deployment, plan_resource_deployment. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Terragrunt GCP Tool MCP.

How many tools does the Terragrunt GCP Tool MCP server expose? +

33 tools across 4 categories: Destructive, Execute, Read, Write. 22 are read-only. 11 can modify, create, or delete data.

How do I enforce a policy on Terragrunt GCP Tool MCP? +

Register the Terragrunt GCP Tool MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Terragrunt GCP Tool MCP tool call.

Deterministic rules across all 33 Terragrunt GCP Tool MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TERRAGRUNT GCP TOOL →

Instant setup, no code required.

33 Terragrunt GCP Tool MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.