The Terraform Cloud MCP server is a powerful integration tool that connects AI assistants with the Terraform Cloud API, enabling natural language interaction for infrastructure management. It works with any MCP-compatible platform including Claude, Claude Code CLI, Claude Desktop, Cursor, and Copilot Studio.
uv package manager (recommended) or pip# Clone the repository
git clone https://github.com/severity1/terraform-cloud-mcp.git
cd terraform-cloud-mcp
# Create virtual environment and activate it
uv venv
source .venv/bin/activate
# Install package
uv pip install .
# Add to Claude Code with your Terraform Cloud token
claude mcp add -e TFC_TOKEN=YOUR_TF_TOKEN -s user terraform-cloud-mcp -- "terraform-cloud-mcp"
Create a configuration file at the appropriate location:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": {
"terraform-cloud-mcp": {
"command": "/path/to/uv",
"args": [
"--directory",
"/path/to/your/terraform-cloud-mcp",
"run",
"terraform-cloud-mcp"
],
"env": {
"TFC_TOKEN": "your_terraform_cloud_token"
}
}
}
}
# Get account information for the authenticated user
account_details = get_account_details()
# List workspaces in an organization
workspaces = list_workspaces(organization="my-org", search="production")
# Get details for a specific workspace
workspace = get_workspace_details(organization="my-org", workspace_name="my-workspace")
# Create a new workspace
new_workspace = create_workspace(
organization="my-org",
name="new-workspace",
params={"description": "Created via MCP", "auto_apply": True}
)
# Lock a workspace to prevent runs
lock_workspace(workspace_id="ws-1234abcd", reason="Maintenance in progress")
# Create and queue a new run
run = create_run(
workspace_id="ws-1234abcd",
params={"message": "Triggered via MCP"}
)
# List runs in a workspace
runs = list_runs_in_workspace(
workspace_id="ws-1234abcd",
page_size=10,
filter_status="applied"
)
# Apply a pending run
apply_run(run_id="run-1234abcd", comment="Approved infrastructure changes")
# Cancel a run in progress
cancel_run(run_id="run-1234abcd", comment="Cancelling due to configuration error")
# Get plan details
plan = get_plan_details(plan_id="plan-1234abcd")
# Get JSON execution plan
plan_json = get_plan_json_output(plan_id="plan-1234abcd")
# Get apply details
apply = get_apply_details(apply_id="apply-1234abcd")
# Get apply logs
logs = get_apply_logs(apply_id="apply-1234abcd")
# Create a new project
project = create_project(
organization="my-org",
name="Infrastructure",
params={"description": "Core infrastructure components"}
)
# List projects
projects = list_projects(organization="my-org")
# Move workspaces to a project
move_workspaces_to_project(
project_id="prj-1234abcd",
workspace_ids=["ws-1234abcd", "ws-5678efgh"]
)
# Get organization details
org = get_organization_details(organization="my-org")
# Get organization entitlements
entitlements = get_organization_entitlements(organization="my-org")
# Create a new organization
new_org = create_organization(
name="new-org",
email="[email protected]",
params={"session_timeout": 20160}
)
# List state versions
state_versions = list_state_versions(
organization="my-org",
workspace_name="my-workspace"
)
# Get current state version
current_state = get_current_state_version(workspace_id="ws-1234abcd")
# Download state file (JSON format)
state_file = download_state_file(state_version_id="sv-1234abcd", json_format=True)
# List state outputs
outputs = list_state_version_outputs(state_version_id="sv-1234abcd")
# Get cost estimate details
cost_estimate = get_cost_estimate_details(cost_estimate_id="ce-1234abcd")
If you encounter issues:
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "terraform-cloud-mcp" '{"command":"terraform-cloud-mcp","env":{"TFC_TOKEN":"${TFC_TOKEN}"}}'See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:
{
"mcpServers": {
"terraform-cloud-mcp": {
"command": "terraform-cloud-mcp",
"env": {
"TFC_TOKEN": "${TFC_TOKEN}"
}
}
}
}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.
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.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json~/.config/Claude/claude_desktop_config.json2. Add this to your configuration file:
{
"mcpServers": {
"terraform-cloud-mcp": {
"command": "terraform-cloud-mcp",
"env": {
"TFC_TOKEN": "${TFC_TOKEN}"
}
}
}
}3. Restart Claude Desktop for the changes to take effect