pickfit

BrowseMCP servers

Terraform MCP Server

An MCP server that connects AI assistants to the Terraform Registry and HCP Terraform/Terraform Enterprise APIs for infrastructure-as-code work.

Tested on Linux

Use it

Linux x86_64

You need first

  • System packages: docker
  • Needs the network
  • Keys or accounts: Terraform Enterprise / HCP Terraform API token (optional, for authenticated tools)
  1. Download the official 1.4.1 linux_amd64 release zip from releases.hashicorp.com, check its SHA256 and unzip the binary into ~/.local/bin

    mkdir -p ~/.local/bin /tmp/tfmcp && cd /tmp/tfmcp && curl -fsSLO https://releases.hashicorp.com/terraform-mcp-server/1.4.1/terraform-mcp-server_1.4.1_linux_amd64.zip && curl -fsSLO https://releases.hashicorp.com/terraform-mcp-server/1.4.1/terraform-mcp-server_1.4.1_SHA256SUMS && grep linux_amd64.zip terraform-mcp-server_1.4.1_SHA256SUMS | sha256sum -c - && unzip -o terraform-mcp-server_1.4.1_linux_amd64.zip -d ~/.local/bin terraform-mcp-server && chmod +x ~/.local/bin/terraform-mcp-server

Check that it works

terraform-mcp-server --version

The output should contain “Version: 1.4.1”.

First thing to try

terraform-mcp-server streamable-http --transport-port 8080 --transport-host 127.0.0.1
curl -sS http://localhost:8080/health

Add it to your agent

claude mcp add terraform-mcp-server -- terraform-mcp-server stdio
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "terraform-mcp-server": {
      "command": "terraform-mcp-server",
      "args": [
        "stdio"
      ]
    }
  }
}

Add terraform-mcp-server stdio as an MCP server in your AI assistant's settings, then ask the assistant about Terraform providers or modules.

What it does

  • Look up Terraform Registry providers, modules and policies
    How to use it
    1. Register terraform-mcp-server stdio as an MCP server in your AI client.
    2. Ask your assistant for registry information, for example the latest version of a provider.
    3. The assistant calls a tool such as get_latest_provider_version with a namespace and name, like hashicorp and aws.
    Tested
  • Manage HCP Terraform and Enterprise workspaces
    Not tested
  • Create, update and delete workspaces and runs
    Not tested
  • Export OpenTelemetry metrics on tool usage
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Connects
  3. 1 of 4 features work
  4. Works offline

Good for

  • look up Terraform provider documentation from an AI assistant
  • manage HCP Terraform workspaces, variables, tags and runs

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 15 Nov 2026
  • Version 1.4.1

An MCP client handshake over stdio listed 9 tools, and a call to get_latest_provider_version returned a result.

Differences the test machine hit

  • README: Install with docker run, or with go install ...@latest
    In the test: Neither Docker nor Go was available. HashiCorp publishes prebuilt binaries at releases.hashicorp.com/terraform-mcp-server, and installing the 1.4.1 linux_amd64 zip worked. The README does not mention these binaries.
  • README: Toolsets: registry, terraform, all
    In the test: Without TFE_TOKEN, only the 9 registry tools are listed, even with --toolsets=all. The HCP Terraform workspace and run tools need a token.
  • README: Registry tools query the public Terraform Registry
    In the test: The tool call in check 6 reaches the public registry over the internet. If the box has no network, this call will fail even though the server works.

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.