tfmcp: Terraform Model Context Protocol Tool
- This project is experimental. Features may change without notice. Use with caution! *
tfmcp is a command-line tool that helps you interact with Terraform via the Model Context Protocol (MCP). It allows LLMs to manage and operate your Terraform environments, including:
Demo
See tfmcp in action with Claude Desktop:
tfmcp Demo with Claude Desktop
- Reading Terraform configuration files
- Analyzing Terraform plan outputs
- Applying Terraform configurations
- Managing Terraform state
- Creating and modifying Terraform configurations
Latest Release
The first stable release of tfmcp (v0.1.1) is now available on Crates.io! You can easily install it using Cargo:
Features
- Terraform Integration
Deeply integrates with the Terraform CLI to analyze and execute operations.
- MCP Server Capabilities
Runs as a Model Context Protocol server, allowing AI assistants to access and manage Terraform.
- Blazing Fast
High-speed processing powered by the Rust ecosystem.
- Automatically creates sample Terraform projects when needed, ensuring smooth operation even for new users.
Installation
From Source
From Crates.io
Requirements
- Rust (edition 2021)
- Terraform CLI installed and available in PATH
- Claude Desktop (for AI assistant integration)
Usage
Integrating with Claude Desktop
To use tfmcp with Claude Desktop:
- If you haven't already, install tfmcp:
- Find the path to your installed tfmcp executable:
- Add the following configuration to
~/Library/Application\ Support/Claude/claude_desktop_config.json:
- Restart Claude Desktop and enable the tfmcp tool.
- tfmcp will automatically create a sample Terraform project in
~/terraformif one doesn't exist, ensuring Claude can start working with Terraform right away. The sample project is based on the examples included in theexample/demodirectory of this repository.
Logs and Troubleshooting
The tfmcp server logs are available at:
Common issues and solutions:
- Claude can't connect to the server: Make sure the path to the tfmcp executable is correct in your configuration
- Terraform project issues: tfmcp automatically creates a sample Terraform project if none is found
- Method not found errors: MCP protocol support includes resources/list and prompts/list methods
Environment Variables
TERRAFORM_DIR: Set this to specify a custom Terraform project directory. If not set, tfmcp will use the directory provided by command line arguments, configuration files, or fall back to~/terraform. You can also change the project directory at runtime using theset_terraform_directorytool.
TFMCP_LOG_LEVEL: Set todebug,info,warn, orerrorto control logging verbosity.
TFMCP_DEMO_MODE: Set totrueto enable demo mode with additional safety features.
Security Considerations
When using tfmcp, please be aware of the following security considerations:
- tfmcp executes Terraform commands on your behalf, which can create, modify, or destroy infrastructure
- In production environments, consider using appropriate IAM permissions and role boundaries
- Review all Terraform plans before applying them, especially when generated by an AI
- Sensitive information in your Terraform state might be accessible to the AI assistants
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature)
- Commit your changes (
git commit -m 'Add some amazing feature')
- Push to the branch (
git push origin feature/amazing-feature)
- Open a Pull Request
Roadmap
Here are some planned improvements and future features for tfmcp:
Completed
- Basic Terraform IntegrationCore integration with Terraform CLI for analyzing and executing operations.
- MCP Server ImplementationInitial implementation of the Model Context Protocol server for AI assistants.
- Automatic Project CreationAdded functionality to automatically create sample Terraform projects when needed.
- Claude Desktop IntegrationSupport for seamless integration with Claude Desktop.
- Core MCP MethodsImplementation of essential MCP methods including resources/list and prompts/list.
- Error Handling ImprovementsBetter error handling and recovery mechanisms for robust operation.
- Dynamic Project Directory SwitchingAdded ability to change the active Terraform project directory without restarting the service.
- Crates.io PublicationPublished the package to Crates.io for easy installation via Cargo.
In Progress
- Enhanced Terraform AnalysisImplement deeper parsing and analysis of Terraform configurations, plans, and state files.
- Multi-Environment SupportAdd support for managing multiple Terraform environments, workspaces, and modules.
- Security EnhancementsImprove security features including better authentication and authorization mechanisms.
- Expanded MCP Protocol SupportImplement additional MCP methods and capabilities for richer integration with AI assistants.
- Interactive TUIDevelop a terminal-based user interface for easier local usage and debugging.
- Cost EstimationIntegrate with cloud provider pricing APIs to provide cost estimates for Terraform plans.
- Performance OptimizationOptimize resource usage and response times for large Terraform projects.
- Integration with Other AI PlatformsExtend beyond Claude to support other AI assistants and platforms.
- Comprehensive Testing FrameworkExpand test coverage including integration tests with real Terraform configurations.
- Plugin SystemDevelop a plugin architecture to allow extensions of core functionality.
License
This project is licensed under the MIT License - see the LICENSE file for details.
tfmcp: Terraform Model Context Protocol Tool
- This project is experimental. Features may change without notice. Use with caution! *
tfmcp is a command-line tool that helps you interact with Terraform via the Model Context Protocol (MCP). It allows LLMs to manage and operate your Terraform environments, including:
Demo
See tfmcp in action with Claude Desktop:
tfmcp Demo with Claude Desktop
- Reading Terraform configuration files
- Analyzing Terraform plan outputs
- Applying Terraform configurations
- Managing Terraform state
- Creating and modifying Terraform configurations
Latest Release
The first stable release of tfmcp (v0.1.1) is now available on Crates.io! You can easily install it using Cargo:
Features
- Terraform Integration
Deeply integrates with the Terraform CLI to analyze and execute operations.
- MCP Server Capabilities
Runs as a Model Context Protocol server, allowing AI assistants to access and manage Terraform.
- Blazing Fast
High-speed processing powered by the Rust ecosystem.
- Automatically creates sample Terraform projects when needed, ensuring smooth operation even for new users.
Installation
From Source
From Crates.io
Requirements
- Rust (edition 2021)
- Terraform CLI installed and available in PATH
- Claude Desktop (for AI assistant integration)
Usage
Integrating with Claude Desktop
To use tfmcp with Claude Desktop:
- If you haven't already, install tfmcp:
- Find the path to your installed tfmcp executable:
- Add the following configuration to
~/Library/Application\ Support/Claude/claude_desktop_config.json:
- Restart Claude Desktop and enable the tfmcp tool.
- tfmcp will automatically create a sample Terraform project in
~/terraformif one doesn't exist, ensuring Claude can start working with Terraform right away. The sample project is based on the examples included in theexample/demodirectory of this repository.
Logs and Troubleshooting
The tfmcp server logs are available at:
Common issues and solutions:
- Claude can't connect to the server: Make sure the path to the tfmcp executable is correct in your configuration
- Terraform project issues: tfmcp automatically creates a sample Terraform project if none is found
- Method not found errors: MCP protocol support includes resources/list and prompts/list methods
Environment Variables
TERRAFORM_DIR: Set this to specify a custom Terraform project directory. If not set, tfmcp will use the directory provided by command line arguments, configuration files, or fall back to~/terraform. You can also change the project directory at runtime using theset_terraform_directorytool.
TFMCP_LOG_LEVEL: Set todebug,info,warn, orerrorto control logging verbosity.
TFMCP_DEMO_MODE: Set totrueto enable demo mode with additional safety features.
Security Considerations
When using tfmcp, please be aware of the following security considerations:
- tfmcp executes Terraform commands on your behalf, which can create, modify, or destroy infrastructure
- In production environments, consider using appropriate IAM permissions and role boundaries
- Review all Terraform plans before applying them, especially when generated by an AI
- Sensitive information in your Terraform state might be accessible to the AI assistants
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature)
- Commit your changes (
git commit -m 'Add some amazing feature')
- Push to the branch (
git push origin feature/amazing-feature)
- Open a Pull Request
Roadmap
Here are some planned improvements and future features for tfmcp:
Completed
- Basic Terraform IntegrationCore integration with Terraform CLI for analyzing and executing operations.
- MCP Server ImplementationInitial implementation of the Model Context Protocol server for AI assistants.
- Automatic Project CreationAdded functionality to automatically create sample Terraform projects when needed.
- Claude Desktop IntegrationSupport for seamless integration with Claude Desktop.
- Core MCP MethodsImplementation of essential MCP methods including resources/list and prompts/list.
- Error Handling ImprovementsBetter error handling and recovery mechanisms for robust operation.
- Dynamic Project Directory SwitchingAdded ability to change the active Terraform project directory without restarting the service.
- Crates.io PublicationPublished the package to Crates.io for easy installation via Cargo.
In Progress
- Enhanced Terraform AnalysisImplement deeper parsing and analysis of Terraform configurations, plans, and state files.
- Multi-Environment SupportAdd support for managing multiple Terraform environments, workspaces, and modules.
- Security EnhancementsImprove security features including better authentication and authorization mechanisms.
- Expanded MCP Protocol SupportImplement additional MCP methods and capabilities for richer integration with AI assistants.
- Interactive TUIDevelop a terminal-based user interface for easier local usage and debugging.
- Cost EstimationIntegrate with cloud provider pricing APIs to provide cost estimates for Terraform plans.
- Performance OptimizationOptimize resource usage and response times for large Terraform projects.
- Integration with Other AI PlatformsExtend beyond Claude to support other AI assistants and platforms.
- Comprehensive Testing FrameworkExpand test coverage including integration tests with real Terraform configurations.
- Plugin SystemDevelop a plugin architecture to allow extensions of core functionality.
License
This project is licensed under the MIT License - see the LICENSE file for details.