tfmcp: Terraform MCP Tool

What is tfmcp?

tfmcp is a command-line tool that helps you interact with Terraform via the Model Context Protocol (MCP). It allows large language models (LLMs) to manage and operate your Terraform environments, including reading configurations, analyzing plans, applying changes, managing state, and creating or modifying Terraform configurations.

How to use tfmcp?

Install tfmcp with cargo install tfmcp or build from source, then run tfmcp mcp to launch it as an MCP server. To integrate with Claude Desktop, configure ~/Library/Application Support/Claude/claude_desktop_config.json pointing to the tfmcp executable with "args": ["mcp"]. You can specify a Terraform project directory via the -d flag, the TERRAFORM_DIR environment variable, or the set_terraform_directory tool at runtime.

Key features of tfmcp

• Deep Terraform CLI integration for analyzing and executing operations
• Runs as a Model Context Protocol server for AI assistants
• Module health analysis with cohesion/coupling metrics and refactoring suggestions
• Resource dependency graph visualization with dot output
• Security scanning with secret detection and configurable policies
• Production-ready audit logging and access restrictions

Use cases of tfmcp

• AI-assisted Terraform configuration creation and modification
• Automated plan analysis with risk scoring and recommendations
• Terraform state inspection and drift detection
• Module registry search and provider information retrieval
• Compliance checks against Terraform guidelines and best practices