MCP server for Terragrunt GCP infrastructure management with experimental features support
Connect Terragrunt Gcp Tool MCP to Claude, Cursor or any other MCP client and it stops being a tab you switch to. MCP server for Terragrunt GCP infrastructure management with experimental features support. The terragrunt gcp tool mcp mcp server is what makes that connection.
A Model Context Protocol (MCP) server tool for managing Google Cloud Platform infrastructure using Terragrunt. This tool provides intelligent automation and management capabilities for the terragrunt-gcp-org-automation codebase with support for Terragrunt Experimental Features.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
list_stacks — List all Terragrunt stacks using experimental featuresget_stack_details — Get detailed information about a specific stack including units and execution orderexecute_stack_command — Execute commands on stacks with parallel execution and dependency managementget_stack_outputs — Get aggregated outputs from stack-level operationsget_enhanced_infrastructure_status — Get comprehensive status including both traditional resources and stacksConfiguration is passed through the environment: GOOGLE_APPLICATION_CREDENTIALS. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
This sits in the cloud and infrastructure group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Terragrunt Gcp Tool MCP's toolset — list_stacks, get_stack_details, execute_stack_command and 2 more — is a fair guide to whether it matches your workflow. It is maintained by spolspol; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Terragrunt Gcp Tool MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| list_stacks | List all Terragrunt stacks using experimental features |
| get_stack_details | Get detailed information about a specific stack including units and execution order |
| execute_stack_command | Execute commands on stacks with parallel execution and dependency management |
| get_stack_outputs | Get aggregated outputs from stack-level operations |
| get_enhanced_infrastructure_status | Get comprehensive status including both traditional resources and stacks |
{
"mcpServers": {
"terragrunt-gcp-autodevops": {
"command": "python3",
"args": [
"/Users/spol/Desktop/GIT/INTI/terragrunt-gcp-tool-mcp/run_server.py",
"/Users/spol/Desktop/GIT/INTI/terragrunt-gcp-tool-mcp/config/config.yaml"
],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/your/gcp-credentials.json"
}
}
},
"global": {
"systemPrompt": "You are an AutoDevOps Infrastructure Assistant with expert knowledge in cloud infrastructure management. You have access to the Terragrunt GCP MCP Tool with comprehensive capabilities for managing Google Cloud Platform infrastructure. ROLE: Help users manage, monitor, and maintain cloud infrastructure efficiently and safely. Always start with visualization using draw_resource_tree or visualize_infrastructure, validate before deployment with validate_resource_config, and follow GitOps best practices."
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| GOOGLE_APPLICATION_CREDENTIALS | Configuration value read at startup. | Optional |
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
AWS Labs' official server suite — current AWS docs, CDK guidance, cost analysis and service tools.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.
Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.