Skip to main content
Glama
cloudcwfranck

@cloudcraftwithfranck/govcloud-mcp

private_endpoint_map

Generates Bicep templates for private endpoints and DNS zones to connect Azure services privately, compliant with FedRAMP/IL standards.

Instructions

Generate the complete private endpoint architecture required for a list of Azure services at a given FedRAMP/IL compliance level. Returns Bicep for every required private endpoint and DNS configuration.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
servicesYesAzure services e.g. ["Key Vault","Storage Account","AKS"]
impactLevelYes
vnetCidrNoVNet CIDR e.g. "10.0.0.0/16"
dnsZoneSubscriptionIdNoSubscription ID for private DNS zones

Implementation Reference

  • The handler function that executes the private_endpoint_map tool logic. It takes validated args, calls Anthropic Claude with an architecture system prompt to generate private endpoint Bicep code, DNS zones, NSG rules, and other Azure networking artifacts.
    export async function handlePrivateEndpoint(args: unknown): Promise<string> {
      return runTool('private_endpoint_map', args, Schema, async ({ services, impactLevel, vnetCidr, dnsZoneSubscriptionId }) => {
        const response = await anthropic.messages.create({
          model: MODEL,
          max_tokens: getTokenBudget('private_endpoint_map'),
          system: ARCHITECTURE_SYSTEM,
          messages: [
            {
              role: 'user',
              content: `Generate the complete private endpoint architecture for these Azure services at ${impactLevel}.
    
    **Services:** ${services.join(', ')}
    **Impact Level:** ${impactLevel}
    ${vnetCidr ? `**VNet CIDR:** ${vnetCidr}` : ''}
    ${dnsZoneSubscriptionId ? `**DNS Zone Subscription:** ${dnsZoneSubscriptionId}` : ''}
    
    Provide:
    1. Which services REQUIRE private endpoints at ${impactLevel} (with NIST control rationale)
    2. Which services RECOMMEND but don't require private endpoints
    3. All private DNS zones needed (exact zone names: privatelink.*.azure.com)
    4. Subnet requirements and CIDR recommendations (with justification)
    5. Complete Bicep for all private endpoints and DNS zone group linkages
    6. NSG rules required to allow private endpoint traffic
    7. DNS forwarding configuration for hybrid on-prem scenarios
    8. GCC High-specific endpoint differences where applicable
    
    Use actual Azure private link DNS zone names and ARM resource types.`,
            },
          ],
        });
    
        return response.content[0].type === 'text' ? response.content[0].text : '';
      });
    }
  • Zod schema for validating inputs: services (array of strings, 1-50 items), impactLevel (enum: fedramp-moderate/fedramp-high/il4/il5), optional vnetCidr and dnsZoneSubscriptionId.
    const Schema = z.object({
      services: z.array(z.string().max(500)).min(1).max(50),
      impactLevel: z.enum(['fedramp-moderate', 'fedramp-high', 'il4', 'il5']),
      vnetCidr: z.string().max(500).optional(),
      dnsZoneSubscriptionId: z.string().max(500).optional(),
    });
  • MCP input schema definition for the private_endpoint_map tool, declaring the JSON Schema for services, impactLevel, vnetCidr, and dnsZoneSubscriptionId parameters.
      inputSchema: {
        type: 'object' as const,
        properties: {
          services: {
            type: 'array',
            items: { type: 'string' },
            description: 'Azure services e.g. ["Key Vault","Storage Account","AKS"]',
          },
          impactLevel: {
            type: 'string',
            enum: ['fedramp-moderate', 'fedramp-high', 'il4', 'il5'],
          },
          vnetCidr: { type: 'string', description: 'VNet CIDR e.g. "10.0.0.0/16"' },
          dnsZoneSubscriptionId: { type: 'string', description: 'Subscription ID for private DNS zones' },
        },
        required: ['services', 'impactLevel'],
      },
    };
  • Missing tool name's default handler returns an error
      default:
        throw new Error(`Unknown tool: ${name}`);
    }
  • Token budget configuration for private_endpoint_map (4096 max_tokens) and timeout configuration (30000ms), both used by the runTool helper.
      private_endpoint_map: 4096,
      devsecops_scorecard: 3072,
      bigbang_validate: 3072,
      gcc_high_guidance: 2048,
      signing_config: 2048,
      azure_service_selector: 2048,
      ironbank_lookup: 1024,
      govcloud_quickstart: 1024,
      bicep_analyze: 4096,
    };
Behavior2/5

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

No annotations provided, so description must disclose behaviors. It states returns Bicep but doesn't mention safety, permissions, or whether it modifies resources. Lacks detail on what 'complete' entails.

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?

Two concise sentences front-loading purpose. Could be improved with structured details (e.g., output format), but no redundancy.

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

Completeness3/5

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

No output schema, so description should detail return value. Says 'returns Bicep' but not the structure or error handling. Given no annotations, more context needed for safe invocation.

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 coverage is 75%, so baseline 3. Description adds no extra meaning beyond schema; it doesn't explain parameters like impactLevel enum or vnetCidr format.

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 tool generates a complete private endpoint architecture for Azure services with compliance levels, distinguishing it from siblings like 'landing_zone_design'. It uses specific verbs and resources.

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 on when to use this tool versus alternatives like 'landing_zone_design' or 'azure_service_selector'. No prerequisites mentioned for parameters like vnetCidr or dnsZoneSubscriptionId.

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/cloudcwfranck/govcloud-mcp'

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