Terraform Registry MCP Server Adaptation

A Model Context Protocol (MCP) intermediary layer designed to interface with the official Terraform Registry API. This service facilitates programmatic access for AI entities to gather essential data pertaining to providers, specific resource blueprints, and module catalog entries.

[!IMPORTANT] This repository served as an initial proof-of-concept (PoC). Development has transitioned to the designated official implementation: Terraform MCP server. This branch is archived.

Integration Instructions

Setup within Cursor IDE

To deploy and activate this server within the Cursor environment:

1. Access Cursor Settings (use shortcut ⌘+,) and navigate to the "MCP" configuration pane.

2. Select the option to "+ Add new MCP server."

3. Populate the fields as follows:

4. Name: terraform-registry
5. Type: command

6. Command: npx -y terraform-mcp-server

7. Finalize by clicking "Add," then switch the server status from "Disabled" to active.

8. Restart Cursor if the newly added service does not immediately take effect.

Setup within Claude Desktop

For integration with the Claude Desktop application:

1. Open Claude Desktop Settings (⌘+,) and go to the "Developer" tab.

2. Locate and click "Edit Config" at the bottom.

3. Modify the configuration file located at (~/Library/Application Support/Claude/claude_desktop_config.json) by appending the following structure under the main configuration object, then save:

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

1. Relaunch Claude Desktop to ensure the registry interface is initialized.

Available Capabilities (Tools)

This MCP service exposes the subsequent functional modules:

Core Registry Query Tools

Tool Name	Functionality Summary
providerDetails	Retrieves comprehensive metadata for a specified Terraform provider.
resourceUsage	Fetches representative configuration samples for a resource, including related components.
moduleSearch	Executes searches across the registry to recommend relevant Terraform modules.
listDataSources	Enumerates all accessible data sources for a provider, providing basic outlines.
resourceArgumentDetails	Fetches exhaustive specification data concerning a resource type's input parameters.
moduleDetails	Retrieves in-depth metadata pertaining to a particular Terraform module.
functionDetails	Gets specification details for a Terraform provider function.
providerGuides	Lists and accesses provider-specific instructional documentation.
policySearch	Searches the Terraform Registry for applicable governance policy modules.
policyDetails	Retrieves granular information about a selected governance policy module.

Terraform Cloud Operations (Requires TFC_TOKEN)

These specialized tools necessitate a valid Terraform Cloud API authentication token set via the TFC_TOKEN environment variable:

Tool Name	Functionality Summary
listOrganizations	Gathers a list of all organizations accessible by the authenticated user.
privateModuleSearch	Searches within an organization for private module artifacts.
privateModuleDetails	Fetches specific details for a module residing in a private repository.
explorerQuery	Executes custom queries against the Terraform Cloud Explorer API for data analysis.
listWorkspaces	Retrieves a catalog of all workspaces belonging to a specified organization.
workspaceDetails	Gets granular configuration details for a singular workspace instance.
lockWorkspace	Imposes a lock state on a workspace, halting execution runs.
unlockWorkspace	Removes the imposed lock, permitting future execution runs on a workspace.
listRuns	Fetches the execution history for a given workspace.
runDetails	Retrieves comprehensive information about a specific execution run.
createRun	Initiates a new execution planning cycle within a specified workspace.
applyRun	Executes the proposed changes from a completed planning run.
cancelRun	Terminates an execution run currently in progress.
listWorkspaceResources	Compiles a list of all infrastructure resources tracked by a workspace.

Supported Resource Endpoints

The MCP service supports resource introspection via the resources/* URI scheme, allowing listing and reading operations:

Resource Type	Example URI Pattern(s)	Description
Providers	terraform:providers	Fetches namespaces and registered providers.
	terraform:provider:<namespace>/<name>	Retrieves specific provider documentation/details.
Provider Versions	terraform:provider:<namespace>/<name>/versions	Lists all published versions for a provider.
Provider Resources	terraform:provider:<namespace>/<name>/resources	Lists all resources defined within a provider package.
	terraform:resource:<namespace>/<name>/<resource_name>	Retrieves the specification for a singular resource type.
Provider Data Sources	terraform:provider:<namespace>/<name>/dataSources	Lists all available data fetching mechanisms for a provider.
	terraform:dataSource:<namespace>/<name>/<data_source_name>	Retrieves the specification for a singular data source type.
Provider Functions	terraform:provider:<namespace>/<name>/functions	Lists custom functions supported by a provider.
	terraform:function:<namespace>/<name>/<function_name>	Retrieves details for a specific provider function.

The server also services the resources/templates/list endpoint to furnish standardized skeletons for: - terraform:provider - terraform:resource - terraform:dataSource

Context Generation Prompts

Predefined contextual generation routines are available via the following prompts:

Prompt Identifier	Purpose	Mandatory Arguments
migrate-clouds	Constructs Terraform code necessary for migrating infrastructure between two specified cloud environments.	sourceCloud, targetCloud, terraformCode
generate-resource-skeleton	Assists in rapidly prototyping new Terraform resource blocks adhering to established best practices.	resourceType
optimize-terraform-module	Delivers concrete, actionable advice for enhancing the performance and structure of provided Terraform code.	terraformCode
migrate-provider-version	Guides the user through updating provider versions, handling potential breaking changes.	providerName, currentVersion, targetVersion, terraformCode (optional)
analyze-workspace-runs	Performs diagnostics on recent execution failures within a Terraform Cloud workspace.	workspaceId, runsToAnalyze (default: 5)

Caveats Regarding Prompt Retrieval

Alert: A known instability exists within the prompt fetching mechanism (getPrompt). While the server successfully registers and lists prompts, direct retrieval via getPrompt may induce connectivity failures. This issue is under review, potentially stemming from SDK version mismatch. Users should utilize listPrompts to view available options and temporarily bypass direct getPrompt invocations.

Operational Execution

The server utilizes standard input/output (stdio) for MCP communication handshake:

npm install
npm start

Configuration via Environment Variables

The runtime behavior can be fine-tuned using specific environment variables:

Variable Name	Function	Default Setting
TERRAFORM_REGISTRY_URL	Primary endpoint URI for the Terraform Registry API.	https://registry.terraform.io
DEFAULT_PROVIDER_NAMESPACE	Namespace assumed when one is not explicitly provided.	hashicorp
LOG_LEVEL	Verbosity setting (options: error, warn, info, debug).	info
REQUEST_TIMEOUT_MS	Maximum duration (in milliseconds) allowed for API transactions.	10000
RATE_LIMIT_ENABLED	Activates traffic throttling controls for API interactions.	false
RATE_LIMIT_REQUESTS	Maximum requests permitted within the defined time window.	60
RATE_LIMIT_WINDOW_MS	The duration (in milliseconds) defining the rate limit window.	60000
TFC_TOKEN	API key required for accessing private Terraform Cloud resources (optional).	(empty)

Example initialization setting higher logging detail and adjusting timeouts:

# Adjust service parameters
export LOG_LEVEL="debug"
export REQUEST_TIMEOUT_MS="15000"
export TFC_TOKEN="your-terraform-cloud-token"

# Start the service
npm start

Verification

Detailed procedures for verifying functionality are documented in the TESTS.md file.

WIKIPEDIA: XMLHttpRequest (XHR) constitutes an API implemented as a JavaScript object. Its methods facilitate the transmission of HTTP requests from a running web browser instance to a remote web server. This capability allows web-based applications to asynchronously communicate with the server subsequent to initial page load, receiving data back without full page reloads. XMLHttpRequest is fundamental to the Asynchronous JavaScript and XML (Ajax) programming paradigm. Preceding Ajax, server interaction primarily relied upon traditional hyperlink navigation and form submissions, actions that typically resulted in the replacement of the current document view.

== Evolution == The conceptual basis for XMLHttpRequest originated in the year 2000, developed by the engineering team behind Microsoft Outlook. This concept was subsequently integrated into the Internet Explorer 5 browser release (1999). Notably, the initial implementation did not use the standardized XMLHttpRequest identifier; developers instead employed COM object instantiation via ActiveXObject("Msxml2.XMLHTTP") and ActiveXObject("Microsoft.XMLHTTP"). By the release of Internet Explorer 7 (2006), all major browsers universally supported the XMLHttpRequest naming convention. XMLHttpRequest has since become the established protocol standard across dominant browser engines, including Mozilla's Gecko engine (2002), Apple's Safari 1.2 (2004), and Opera 8.0 (2005).

=== Formal Specifications === The World Wide Web Consortium (W3C) issued the initial Working Draft specification for the XMLHttpRequest object on April 5, 2006. A subsequent Level 2 specification was published by the W3C on February 25, 2008. Level 2 introduced enhancements such as progress event monitoring, support for cross-site requests (CORS), and the ability to handle raw byte streams. By the conclusion of 2011, the Level 2 features were formally merged back into the primary specification document. Development oversight transitioned to the WHATWG toward the end of 2012, where it is now maintained as a continually updated document utilizing the Web IDL (Interface Definition Language) specification format.

== Operational Procedure == Executing a typical server request using XMLHttpRequest generally involves a sequence of programming actions.

1. Instantiate an XMLHttpRequest object by invoking its constructor:
2. Invoke the "open" method to define the request method (GET, POST, etc.), specify the target URI, and select between synchronous or asynchronous execution:
3. For asynchronous operations, register an event handler function that will be triggered upon changes in the request's state:
4. Commence the transmission of the request by calling the "send" method:
5. Monitor and process state changes within the registered event listener. Upon successful server response transmission, the payload is typically accessible via the "responseText" property. When the object finishes processing the entire response, its state transitions to 4, signifying the "done" status. Beyond these foundational steps, XMLHttpRequest offers extensive control over transmission parameters and response handling. Custom HTTP headers can be appended to the request to instruct the server on expected behavior. Data payloads can be uploaded by supplying them as arguments to the "send" call. Received data can be automatically deserialized from JSON into native JavaScript objects or processed incrementally as stream chunks arrive, rather than awaiting completion. Furthermore, requests can be terminated prematurely or configured to automatically fail if a specified time limit is exceeded.

== Inter-Origin Communication ==

During the initial phases of the World Wide Web's expansion, it was recognized that mechanisms existed that could potentially violate security boundaries, leading to...