Terraform MCP Server
Terraform Registry and HCP Terraform APIs interaction for IaC workflows.
Data last scanned today · Reviewed today
Overview
The Terraform MCP Server provides a direct bridge between your AI tools and the Terraform ecosystem. It exposes capabilities for interacting with the Terraform Registry and HCP Terraform APIs, allowing AI assistants to query resources and manage infrastructure-related tasks efficiently. The server supports multiple transport protocols, including Stdio and StreamableHTTP, and offers features like token passthrough and client IP forwarding. These options enable flexible deployment patterns, from local execution to centralized setups with specific security considerations.
Our verdict
With a security score of 50/100, this server is currently classified as high-risk. This assessment is driven by the fact that the server is community-maintained rather than developed by the official vendor, and critical security aspects like read-only mode validation and authentication methods have not yet been editorially reviewed. It is suitable for developers experimenting in non-sensitive environments who are prepared to perform their own thorough security validation before deployment.
- Zero direct dependencies minimize supply-chain surface area.
- Active development with commits occurring daily.
- Comprehensive documentation for various client integrations.
- Broad support for both Stdio and StreamableHTTP transports.
- Community-maintained status lacks official vendor oversight.
- Read-only mode implementation has not undergone external audit.
- Authentication mechanisms remain unverified for secure production use.
Tools
| Tool | Description | Risk |
|---|---|---|
| search_providers | Search for providers in the registry | low |
| get_provider_details | Get detailed information about a specific provider | low |
| list_workspaces | List available workspaces | low |
Compatibility
| Client | Local | Docker | Remote | Read-only |
|---|---|---|---|---|
| ChatGPT | ||||
| Claude Desktop | ||||
| Cursor | ||||
| VS Code | ||||
| Windsurf |
Frequently asked questions
›What transport modes does the Terraform MCP server support?
The server supports both Stdio and StreamableHTTP transports with configurable endpoints.
›What are the primary prerequisites for using this server?
You must have Docker installed and running for containerized environments, and an AI assistant that supports the Model Context Protocol.
›Can I use the server with any MCP client?
The documentation warns against using the server with untrusted MCP clients or LLMs because it may expose Terraform data to the client and model.
›How is the Terraform Enterprise or HCP Terraform address configured in streamable-http mode?
In streamable-http mode, the address must be set using the TFE_ADDRESS environment variable, as it cannot be provided by clients via headers or query parameters.
›How can I monitor tool usage and performance?
The server includes OpenTelemetry (OTel) metrics integration to track tool-call volume, latency, and failures when running in StreamableHTTP mode.
Alternatives
Changelog
Badge
Maintain this server? Add the live badge to your README.