What are the prerequisites for running the Terraform MCP Server?
You need Docker installed and running, plus an AI assistant that supports the Model Context Protocol (MCP).
@hashicorp
基本信息
The Terraform MCP Server provides seamless integration with Terraform ecosystem, enabling advanced automation and interaction capabilities for Infrastructure as Code (IaC) development.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"terraform-mcp-server": {
"command": "docker",
"args": [
"run",
"-p",
"8080:8080",
"--rm",
"-e",
"TRANSPORT_MODE=streamable-http",
"-e",
"TRANSPORT_HOST=0.0.0.0",
"hashicorp/terraform-mcp-server"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
The Terraform MCP Server is a Model Context Protocol server that integrates with Terraform Registry APIs, HCP Terraform, and Terraform Enterprise. It enables AI assistants to manage Infrastructure as Code workflows, including workspace operations, provider/module lookups, and run management.
Run the server as a Docker container configured via environment variables. Connect it to an MCP-compatible assistant (VS Code, Cursor, Claude Desktop, etc.). Use the terraform-mcp-server stdio or terraform-mcp-server streamable-http command, or the equivalent Docker command, depending on your chosen transport mode. Set required environment variables like TFE_TOKEN, TFE_ADDRESS, and optionally TRANSPORT_MODE.
You need Docker installed and running, plus an AI assistant that supports the Model Context Protocol (MCP).
Depending on the query, the server may expose certain Terraform data to the MCP client and LLM. Do not use it with untrusted MCP clients or LLMs.
Configure it via environment variables such as `TFE_ADDRESS`, `TFE_TOKEN`, and `TRANSPORT_MODE`. For StreamableHTTP mode you can set host, port, TLS, rate limits, and an organization allowlist.
Enable OpenTelemetry
Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.
Put the project you are working on online. Deploys the current folder or a GitHub repo to a live HTTPS URL on Dockhold; reads status and logs, sets variables, resizes apps and databases...
MCP server for Backblaze B2 Cloud Storage: a focused, safe 40-tool surface (17 native B2 SDK, 19 S3 data-plane, 4 analytics) for any MCP-compatible AI client, currently incubating in Backblaze-Labs

Your AI can finally reach the physical world. Kilo is an AI-first IoT platform for commercial and industrial operations, and this connector hands a live deployment to the AI client you already use. Not an export. Not a

Web hosting for websites built with AI. Connect your HostingFor.AI account and your AI assistant can publish and maintain your site directly: upload files, manage DNS records for custom domains, run SQL against your MySQ
评论