Terraform Registry MCP server

Integrates with the Terraform Registry API to enable provider lookup, resource usage examples, module recommendations, and schema details retrieval for infrastructure-as-code development.
Back to servers
Setup instructions
Provider
Paul Thrasher
Release date
Feb 24, 2025
Language
TypeScript
Package
Stats
3.3K downloads
117 stars

The Terraform Registry MCP server provides a Model Context Protocol interface for interacting with the Terraform Registry API, allowing AI agents to query provider information, resource details, and module metadata.

Installation

Installing in Cursor

To install and use this MCP server in Cursor:

  1. In Cursor, open Settings (⌘+,) and navigate to the "MCP" tab.

  2. Click "+ Add new MCP server."

  3. Enter the following:

    • Name: terraform-registry
    • Type: command
    • Command: npx -y terraform-mcp-server
  4. Click "Add" then scroll to the server and click "Disabled" to enable the server.

  5. Restart Cursor, if needed, to ensure the MCP server is properly loaded.

Installing in Claude Desktop

To install and use this MCP server in Claude Desktop:

  1. In Claude Desktop, open Settings (⌘+,) and navigate to the "Developer" tab.

  2. Click "Edit Config" at the bottom of the window.

  3. Edit the config file to add the following code, then Save the file:

{
  "mcpServers": {
    "terraform-registry": {
      "command": "npx",
      "args": ["-y", "terraform-mcp-server"]
    }
  }
}
  1. Restart Claude Desktop to ensure the MCP server is properly loaded.

Available Tools

Core Registry Tools

Tool Description
providerDetails Gets detailed information about a Terraform provider
resourceUsage Gets example usage of a Terraform resource and related resources
moduleSearch Searches for and recommends Terraform modules based on a query
listDataSources Lists all available data sources for a provider and their basic details
resourceArgumentDetails Fetches comprehensive details about a resource type's arguments
moduleDetails Retrieves detailed metadata for a Terraform module
functionDetails Gets details about a Terraform provider function
providerGuides Lists and views provider-specific guides and documentation
policySearch Searches for policy libraries in the Terraform Registry
policyDetails Gets detailed information about a specific policy library

Terraform Cloud Tools

These tools require a Terraform Cloud API token (TFC_TOKEN):

Tool Description
listOrganizations Lists all organizations the authenticated user has access to
privateModuleSearch Searches for private modules in an organization
privateModuleDetails Gets detailed information about a private module
explorerQuery Queries the Terraform Cloud Explorer API to analyze data
listWorkspaces Lists workspaces in an organization
workspaceDetails Gets detailed information about a specific workspace
lockWorkspace Locks a workspace to prevent runs
unlockWorkspace Unlocks a workspace to allow runs
listRuns Lists runs for a workspace
runDetails Gets detailed information about a specific run
createRun Creates a new run for a workspace
applyRun Applies a run that's been planned
cancelRun Cancels a run that's in progress
listWorkspaceResources Lists resources in a workspace

Supported Resources

The MCP server supports the following resource URIs:

Resource Type Example URI(s)
Providers terraform:providers
terraform:provider:<namespace>/<name>
Provider Versions terraform:provider:<namespace>/<name>/versions
Provider Resources terraform:provider:<namespace>/<name>/resources
terraform:resource:<namespace>/<name>/<resource_name>
Provider Data Sources terraform:provider:<namespace>/<name>/dataSources
terraform:dataSource:<namespace>/<name>/<data_source_name>
Provider Functions terraform:provider:<namespace>/<name>/functions
terraform:function:<namespace>/<name>/<function_name>

Available Prompts

The server provides the following prompts for generating contextual responses:

Prompt Description Required Arguments
migrate-clouds Generate Terraform code to migrate infrastructure between cloud providers sourceCloud, targetCloud, terraformCode
generate-resource-skeleton Helps users quickly scaffold new Terraform resources with best practices resourceType
optimize-terraform-module Provides actionable recommendations for improving Terraform code terraformCode
migrate-provider-version Assists with provider version upgrades and breaking changes providerName, currentVersion, targetVersion, terraformCode (optional)
analyze-workspace-runs Analyzes recent run failures and provides troubleshooting guidance workspaceId, runsToAnalyze (optional, default: 5)

Known Issues with Prompts

Note: There is a known issue with the getPrompt functionality that can cause server crashes. The server properly registers prompts and can list them, but direct requests using the getPrompt method may cause connectivity issues.

Running the Server

The server runs using stdio transport for MCP communication:

npm install
npm start

Configuration with Environment Variables

You can configure the server using these environment variables:

Environment Variable Description Default Value
TERRAFORM_REGISTRY_URL Base URL for Terraform Registry API https://registry.terraform.io
DEFAULT_PROVIDER_NAMESPACE Default namespace for providers hashicorp
LOG_LEVEL Logging level (error, warn, info, debug) info
REQUEST_TIMEOUT_MS Timeout for API requests in milliseconds 10000
RATE_LIMIT_ENABLED Enable rate limiting for API requests false
RATE_LIMIT_REQUESTS Number of requests allowed in time window 60
RATE_LIMIT_WINDOW_MS Time window for rate limiting in milliseconds 60000
TFC_TOKEN Terraform Cloud API token for private registry access

Example usage with environment variables:

# Set environment variables
export LOG_LEVEL="debug"
export REQUEST_TIMEOUT_MS="15000"
export TFC_TOKEN="your-terraform-cloud-token"

# Run the server
npm start

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "terraform-registry" '{"command":"npx","args":["-y","terraform-mcp-server"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "terraform-registry": {
            "command": "npx",
            "args": [
                "-y",
                "terraform-mcp-server"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "terraform-registry": {
            "command": "npx",
            "args": [
                "-y",
                "terraform-mcp-server"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later