Skip to main content
Glama
code-alchemist01

MCP Cloud Services Server

start_resource

Start cloud instances or functions on AWS, Azure, or GCP by specifying the provider and resource ID.

Instructions

Start a cloud resource (instance, function, etc.)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
providerYesCloud provider
resourceIdYesResource ID to start
resourceTypeYesResource type

Implementation Reference

  • The handler logic for the 'start_resource' tool within the handleResourceManagementTool function. It starts an AWS EC2 instance if provider is 'aws' and type is 'instance'; otherwise throws an error.
    case 'start_resource': {
      const resourceId = params.resourceId as string;
      const resourceType = params.resourceType as string;
    
      if (provider === 'aws' && resourceType === 'instance') {
        const adapter = new AWSAdapter();
        await adapter.startEC2Instance(resourceId);
        return { success: true, message: `Instance ${resourceId} started` };
      }
      throw new Error(`Start operation not yet implemented for ${provider} ${resourceType}`);
    }
  • The tool schema definition for 'start_resource', including name, description, and input schema for provider, resourceId, and resourceType.
    {
      name: 'start_resource',
      description: 'Start a cloud resource (instance, function, etc.)',
      inputSchema: {
        type: 'object',
        properties: {
          provider: {
            type: 'string',
            enum: ['aws', 'azure', 'gcp'],
            description: 'Cloud provider',
          },
          resourceId: {
            type: 'string',
            description: 'Resource ID to start',
          },
          resourceType: {
            type: 'string',
            enum: ['instance', 'function'],
            description: 'Resource type',
          },
        },
        required: ['provider', 'resourceId', 'resourceType'],
      },
    },
  • src/server.ts:70-71 (registration)
    Registration and routing logic in the main MCP server handler: checks if the tool name matches one in resourceManagementTools and delegates to handleResourceManagementTool.
    } else if (resourceManagementTools.some((t) => t.name === name)) {
      result = await handleResourceManagementTool(name, args || {});
  • src/server.ts:50-53 (registration)
    Registers the list of all tools (including start_resource via resourceManagementTools spread into allTools) with the MCP server for the ListTools request.
    this.server.setRequestHandler(ListToolsRequestSchema, async () => {
      return {
        tools: allTools,
      };
Behavior2/5

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

No annotations are provided, so the description carries full burden. It states the action ('Start') which implies a mutation operation, but doesn't disclose behavioral traits like required permissions, potential costs, side effects (e.g., billing starts), rate limits, or what happens if the resource is already running. This leaves significant gaps for safe agent invocation.

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

Conciseness5/5

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

The description is a single, efficient sentence that front-loads the core purpose ('Start a cloud resource') and adds brief examples for clarity. Every word earns its place with no redundancy or unnecessary elaboration.

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 complexity of starting cloud resources (a mutation with potential cost/security implications), no annotations, and no output schema, the description is incomplete. It lacks critical context like success/failure behavior, return values, error conditions, or dependencies on other tools (e.g., verifying resource existence first). This makes it inadequate for safe agent operation.

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

Parameters3/5

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

Schema description coverage is 100%, providing full documentation of the three parameters (provider, resourceId, resourceType) with enums and descriptions. The description adds no parameter-specific semantics beyond implying general cloud resource starting, so it meets the baseline of 3 without compensating for any schema gaps.

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

Purpose4/5

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

The description clearly states the action ('Start') and target ('a cloud resource'), with examples of resource types ('instance, function, etc.'). It distinguishes from obvious siblings like 'stop_resource' and 'delete_resource' by specifying the 'start' action, but doesn't explicitly differentiate from provider-specific tools like 'aws_start_ec2_instance'.

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. It doesn't mention when to prefer provider-specific tools (e.g., 'aws_start_ec2_instance') or other related tools like 'get_resource' for checking status. The description implies a general-purpose start function but offers no context about prerequisites, permissions, or appropriate scenarios.

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/code-alchemist01/Cloud-mcp_server'

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