Skip to main content
Glama

terraform

Execute Terraform commands to manage infrastructure as code, including init, plan, apply, and destroy operations for cloud resource provisioning and configuration.

Instructions

Execute Terraform commands (init, plan, apply, destroy, validate, output, etc.)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYes
workingDirYes
varFilesNo
varsNo
autoApproveNo
useLocalstackNo
backendConfigNo
stateNo
targetNo
lockTimeoutNo
refreshNo
workspaceNo

Implementation Reference

  • Main handler function that constructs and executes Terraform (or tflocal) commands based on input parameters like action, working directory, variables, etc., handling different actions such as init, plan, apply, destroy.
    export async function terraformOperations(options: TerraformOptions): Promise<string> {
      const { 
        action, 
        workingDir, 
        varFiles, 
        vars, 
        useLocalstack, 
        autoApprove, 
        backendConfig, 
        state,
        target,
        lockTimeout,
        refresh,
        workspace
      } = options;
      
      // Determine if we should use terraform or tflocal command
      const terraformCmd = useLocalstack ? 'tflocal' : 'terraform';
    
      // If using tflocal, verify it's installed
      if (useLocalstack) {
        await verifyTflocalInstalled();
      } else {
        // Otherwise, verify terraform is installed
        await verifyTerraformInstalled();
      }
    
      // Base command with terraform/tflocal and action
      let command = `cd "${workingDir}" && ${terraformCmd} ${action}`;
    
      // Add var files if specified
      if (varFiles && varFiles.length > 0) {
        command += ' ' + varFiles.map(file => `-var-file="${file}"`).join(' ');
      }
    
      // Add vars if specified
      if (vars && Object.keys(vars).length > 0) {
        command += ' ' + formatCommandParams(vars, '-var');
      }
    
      // Add backend config if specified
      if (backendConfig && Object.keys(backendConfig).length > 0) {
        command += ' ' + formatCommandParams(backendConfig, '-backend-config');
      }
    
      // Add specific parameters based on action
      switch (action) {
        case 'init':
          // No special options needed here
          break;
          
        case 'apply':
        case 'destroy':
          // Add auto-approve if specified
          if (autoApprove) {
            command += ' -auto-approve';
          }
          
          // Add refresh option
          if (refresh !== undefined) {
            command += ` -refresh=${refresh ? 'true' : 'false'}`;
          }
          
          // Add state file if specified
          if (state) {
            command += ` -state="${state}"`;
          }
          
          // Add targets if specified
          if (target && target.length > 0) {
            command += ' ' + target.map(t => `-target="${t}"`).join(' ');
          }
          
          // Add lock timeout if specified
          if (lockTimeout) {
            command += ` -lock-timeout=${lockTimeout}`;
          }
          break;
          
        case 'plan':
          // Add refresh option
          if (refresh !== undefined) {
            command += ` -refresh=${refresh ? 'true' : 'false'}`;
          }
          
          // Add state file if specified
          if (state) {
            command += ` -state="${state}"`;
          }
          
          // Add targets if specified
          if (target && target.length > 0) {
            command += ' ' + target.map(t => `-target="${t}"`).join(' ');
          }
          
          // Add lock timeout if specified
          if (lockTimeout) {
            command += ` -lock-timeout=${lockTimeout}`;
          }
          break;
          
        case 'workspace':
          // Add workspace name if specified
          if (workspace) {
            command += ` select ${workspace}`;
          } else {
            command += ' list'; // Default to listing workspaces if no name is provided
          }
          break;
          
        // For other actions (validate, output, import), no special handling needed
      }
    
      // For debug purposes
      console.log(`Executing Terraform command: ${command}`);
    
      try {
        // Execute the command
        const { stdout, stderr } = await execAsync(command);
        
        // Adjust output based on action
        switch (action) {
          case 'output':
            // Try to parse JSON output
            try {
              const outputJson = JSON.parse(stdout);
              return JSON.stringify(outputJson, null, 2);
            } catch (error) {
              // If not JSON, return as is
              return stdout;
            }
            
          default:
            return stdout || `Terraform ${action} completed successfully (no output).`;
        }
      } catch (error: any) {
        const errorMessage = error.stderr || error.message || 'Unknown error';
        throw new AnsibleExecutionError(`Terraform execution failed for ${action}: ${errorMessage}`, error.stderr);
      }
    }
  • Zod schema defining the input parameters for the terraform tool, including action enum, working directory, variables, and action-specific options.
    export const TerraformSchema = z.object({
      action: TerraformActionEnum,
      workingDir: z.string().min(1, 'Working directory is required'),
      varFiles: z.array(z.string()).optional(),
      vars: z.record(z.any()).optional(),
      autoApprove: z.boolean().optional().default(false),
      useLocalstack: z.boolean().optional().default(false),
      backendConfig: z.record(z.string()).optional(),
      state: z.string().optional(),
      target: z.array(z.string()).optional(),
      lockTimeout: z.string().optional(),
      refresh: z.boolean().optional().default(true),
      workspace: z.string().optional()
    });
    
    export type TerraformOptions = z.infer<typeof TerraformSchema>;
  • Registration of the 'terraform' tool in the toolDefinitions map, linking to its description, schema, and handler function.
    terraform: {
      description: 'Execute Terraform commands (init, plan, apply, destroy, validate, output, etc.)',
      schema: terraform.TerraformSchema,
      handler: terraform.terraformOperations,
    },
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions commands like 'destroy' which implies destructive operations, but doesn't warn about risks, confirmations needed, or that 'autoApprove' parameter can bypass prompts. It also omits details like execution time, error handling, or output format. The description adds minimal behavioral context beyond the command names.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that lists key commands, making it front-loaded and appropriately sized. However, it could be more structured by grouping commands (e.g., core vs. auxiliary) or adding brief context. Every word earns its place, but it's slightly under-specified given the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the high complexity (12 parameters, nested objects, no output schema, and no annotations), the description is incomplete. It doesn't cover parameter meanings, behavioral risks, output expectations, or differentiation from siblings. For a powerful infrastructure tool with many options, this minimal description leaves significant gaps in understanding how to use it effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for 12 undocumented parameters. The description only lists command names (e.g., init, plan) which correspond to the 'action' enum, but doesn't explain other parameters like 'workingDir', 'varFiles', 'vars', or 'autoApprove'. It fails to add meaningful semantics beyond what's inferable from parameter names, leaving most parameters unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool 'Execute Terraform commands' with a non-exhaustive list of examples (init, plan, apply, etc.), which gives a general purpose. However, it's vague about what Terraform is (infrastructure as code tool) and doesn't distinguish it from sibling tools like AWS CloudFormation or other infrastructure management tools. The verb 'execute' is clear but the resource scope is ambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. The description doesn't mention when to choose Terraform over sibling tools like aws_cloudformation for infrastructure management, or when to use specific Terraform commands (e.g., apply vs. plan). There's no context about prerequisites, such as needing Terraform configuration files in the working directory.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/tarnover/mcp-sysoperator'

If you have feedback or need assistance with the MCP directory API, please join our Discord server