Terraform Registry MCP Server

A Model Context Protocol (MCP) server that provides tools for interacting with the Terraform Registry API. This server enables 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 file (~/Library/Application Support/Claude/claude_desktop_config.json) to add the following code, then Save the file.

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

4. Restart Claude Desktop to ensure the MCP server is properly loaded.

Testing

For information about testing this project, please see the TESTS.md file.

Tools

1. Provider Lookup

Looks up Terraform provider details by name, returning the latest version and version count.

Input:

{
  "provider": "aws",             // Required: Provider name
  "namespace": "hashicorp",      // Optional: Provider namespace (defaults to "hashicorp")
  "version": "latest"            // Optional: Provider version
}

Output:

{
  "content": [
    {
      "type": "text",

            
        
            
                      "text": "Provider hashicorp/aws: latest version is 5.0.0 (out of 150 versions)."
    }
  ]
}

2. Resource Usage

Gets example usage of a Terraform resource and related resources.

Input:

{
  "provider": "aws",             // Required: Provider name
  "resource": "aws_instance"     // Required: Resource name
}

Output:

{
  "content": [
    {
      "type": "text",
      "text": "Example usage for aws_instance:\n```terraform\n[example code]\n```\nRelated resources: aws_vpc, aws_subnet"
    }
  ]
}

3. Module Recommendations

Searches for and recommends Terraform modules based on a query.

Input:

{
  "query": "vpc",                // Required: Search query
  "provider": "aws"              // Optional: Filter modules by provider
}

Output:

{
  "content": [
    {
      "type": "text",
      "text": "Recommended modules for \"vpc\":\n1. terraform-aws-modules/vpc (aws) - AWS VPC Terraform module\n..."
    }
  ]
}

4. Data Source Lookup

Retrieves available data source identifiers for a given Terraform provider.

Input:

{
  "provider": "aws",             // Required: Provider name
  "namespace": "hashicorp"       // Required: Provider namespace
}

Output:

{
  "content": [{
    "type": "text",
    "text": {
      "data_sources": ["aws_ami", "aws_instance", "aws_vpc", ...]
    }
  }]
}

5. Resource Argument Details

Fetches comprehensive details about a specific resource type's arguments, including required and optional attributes, nested blocks, and their descriptions.

Input:

{
  "provider": "aws",             // Required: Provider name
  "namespace": "hashicorp",      // Required: Provider namespace
  "resource": "aws_instance"     // Required: Resource name
}

Output:

Resource: aws_instance

REQUIRED ATTRIBUTES:
  * ami (string)
      The AMI to use for the instance.

OPTIONAL ATTRIBUTES:
  * instance_type (string)

            
        
            
                      The type of instance to start. Updates to this field will trigger a stop/start of the EC2 instance.
  * availability_zone (string) (computed)
      The AZ where the instance will be created.

BLOCKS:
  * network_interface (min: 0, max: 0)
      Customize network interfaces to be attached at instance boot time.
      ATTRIBUTES:
        - network_interface_id (string)
          ID of the network interface to attach.
        - device_index (number) (required)
          Integer index of the network interface attachment.

For full documentation, visit: https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/instance

6. Module Details

Retrieves detailed metadata for a Terraform module.

Input:

{
  "namespace": "terraform-aws-modules",  // Required: Module namespace
  "module": "vpc",                       // Required: Module name
  "provider": "aws"                      // Required: Provider name
}

Output:

{
  "content": [{
    "type": "text",
    "text": {
      "versions": ["5.0.0", "4.0.0", ...],
      "inputs": [
        {
          "name": "region",
          "description": "AWS region to deploy into.",
          "default": "us-east-1"
        },
        ...
      ],
      "outputs": [
        {
          "name": "vpc_id",
          "description": "ID of the VPC created."
        },
        ...
      ],
      "dependencies": []
    }
  }]
}

Running the Server

The server runs using stdio transport for MCP communication:

npm install
npm start

Configuration with Environment Variables

The server can be configured using 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 |

Example usage with environment variables:

# Set environment variables
export LOG_LEVEL="debug"
export REQUEST_TIMEOUT_MS="15000"

# Run the server
node dist/index.js

Testing

See the TESTS.md file for information about testing this project.