Terraform MCP in Claude Code

Quick answer: Install the Terraform MCP server with npx -y mcp-server-terraform --root=/Users/you/infra, add the JSON block below to ~/.claude/settings.json, restart Claude Code, and run /mcp to confirm the connection. Setup runs about 5 minutes on a fresh machine, verified on mcp-server-terraform as of April 15, 2026.

The Terraform MCP server hands Claude Code a tool surface on top of the Terraform CLI. After setup, the model can run init, plan, apply, and destroy, inspect state, and look up provider documentation. The server is published as mcp-server-terraform and runs local terraform binaries, so no cloud credentials beyond what your providers already need.

This guide covers what you get after the wiring is done, the exact config, verification steps, prompt patterns that tend to work well, and the 4 issues that trip people up most often in the first week.

What you get when it is connected

Once the Terraform server is attached, Claude Code can call the server tools from inside any conversation. You do not invoke the tools by hand. When you ask Claude a question the model decides which tool to call and parses the response for you. For teams that live inside Terraform day to day, this replaces dozens of context switches per week with a single line in chat.

Tools exposed include run_init, run_plan, run_apply, run_destroy, show_state, list_resources, list_workspaces, select_workspace, get_provider_docs. The server runs terraform in whatever working directory you nominate with --root. For multi-module setups, a separate server instance per root keeps state scoped.

Prerequisites

A local terraform binary on PATH (version 1.5+). Any provider credentials the configs need (AWS creds, GCP service account, etc) already configured in the shell Claude Code inherits. Node 20 or later.

If you use a version manager like nvm or asdf for Node, confirm the version Claude Code inherits. Open a terminal, run node -v, and note the output. Claude Code uses the Node it sees on PATH at launch, so a shell profile that sets the right version is the reliable path.

Install via npx

Run the package once with npx to verify it starts cleanly:

npx -y mcp-server-terraform --root=/Users/you/infra

The first run downloads the package (a few MB) and starts the server on stdio. The server does not print much on success - it waits for MCP protocol messages on stdin. Press Ctrl-C to stop it. The actual runtime setup happens through Claude Code itself in the next step.

If the install fails with a network error, your npm registry may be blocked. Set npm config set registry https://registry.npmjs.org and retry. Behind a corporate proxy, also set HTTP_PROXY and HTTPS_PROXY in your shell.

Add the config block to ~/.claude/settings.json

Open ~/.claude/settings.json in your editor. If the file does not exist yet, create it with {} as the starting content. Add an mcpServers object with an entry for this server:

{
  "mcpServers": {
    "terraform": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-terraform",
        "--root=/Users/you/infra"
      ]
    }
  }
}

Save the file. If you already have other MCP servers defined, merge the new entry into the existing mcpServers object rather than replacing it.

Restart Claude Code fully (quit and reopen, not just close the window). The server is spawned lazily on the first tool call in a session, not at launch, but the config is read once per Claude Code start.

Verify the connection

Open a new Claude Code session and type /mcp at the prompt. You should see the server listed with a green or connected indicator. If it shows as failed, click into it for the stderr output - the error message usually points at the problem directly (bad token, wrong path, missing Node).

Run a trivial first prompt to confirm round trips work. Good smoke tests:

• For read servers: ask for a list of whatever resource type it exposes.
• For write servers: ask for a describe on a known resource first, then try a safe write on a test resource.

If the first prompt works, the wiring is done. From here on you interact with the server purely through normal prompts in Claude Code.

Example prompts that work well

Here are prompts that tend to get good responses once the server is attached:

• Run terraform plan in the networking module and summarize the additions, changes, and destructions.
• Show me every resource currently in the state file for the production workspace.
• Look up the documentation for the aws_s3_bucket resource and tell me the argument for versioning.
• Apply the pending plan file plan.out in the storage module and report the outputs.
• Find any resource in state whose name contains the word deprecated and list them.
• Run terraform validate in the main module and tell me whether the config is syntactically correct.

Claude will chain tool calls on its own when the prompt implies several steps. For a summarize-then-write flow the model will often call read tools first, then a single write tool at the end. If a prompt keeps burning tool calls, narrow it: specify the resource ID, the time range, or the exact field you want rather than asking Claude to scan everything.

Environment variable security

No MCP-specific env vars. Terraform itself reads provider credentials from standard locations: AWS_ACCESS_KEY_ID and friends for AWS, GOOGLE_APPLICATION_CREDENTIALS for GCP, ARM_CLIENT_ID for Azure. Make sure those are set in the shell Claude Code was launched from so terraform subprocesses pick them up. Never commit .tfvars files that hold secrets.

A general rule across every MCP server: never paste secrets directly into settings.json that lives in a shared or git-tracked directory. Keep the actual secret values in your shell profile (~/.zshrc, ~/.bashrc, or a 1Password-cli helper), export them at shell start, and reference the variable names from the Claude config. That way the secret stays on your machine and the config file is safe to share with teammates.

On macOS, terminals launched from Spotlight or from the Dock both inherit the shell profile. If you launch Claude Code from a GUI shortcut that does not go through a shell, env vars may not propagate - launch from a terminal instead.

Troubleshooting

Plan fails with no valid credentials. Terraform providers cannot authenticate. Check the provider docs for which env vars or config files they read, and confirm they are set in the shell running Claude Code. A quick terraform plan from the same terminal confirms.

State lock blocks applies. Another terraform run or a crashed run left a lock. Run terraform force-unlock LOCK_ID carefully from a terminal. Never force-unlock unless you are sure no other apply is in flight.

Module not found after init. Modules under module blocks need terraform init to run first. The MCP server exposes an init tool; ask Claude to call it before plan or apply on a fresh checkout.

Large plans truncate in tool output. Ask Claude to save plan output to a file via terraform plan -out=plan.out -detailed-exitcode and then show individual resources, rather than dumping the whole plan into one response.

For any issue not listed here, the first step is /mcp inside Claude Code to see the current status and any recent stderr from the server. The second step is running the exact npx command from your terminal to see if the server starts cleanly outside Claude Code. Between those two checks, most problems become obvious within a minute.

Next steps

Once the Terraform server is attached and verified, the useful next move is writing a short prompt template you keep in your notes. List the 3 or 4 prompts you run most often against this server, and paste them into Claude Code when needed. Over a few weeks you build a personal command library that gets real work done without typing much.

For team projects, commit a .mcp.json at the repo root with the same structure. Everyone on the team gets the server wired up automatically on first open, and individual secrets stay in shell profiles. That is the setup pattern that scales past a single developer.