Skip to main content
Glama
cloudcwfranck

@cloudcraftwithfranck/govcloud-mcp

bigbang_harden

Generate a fully hardened Big Bang values.yaml targeting DoD IL4 or IL5, starting from scratch or an existing file. Includes digest-pinned images from Chainguard or Iron Bank.

Instructions

Generate a fully hardened Big Bang values.yaml targeting DoD IL4 or IL5 from scratch or from an existing values file. Includes Chainguard/Iron Bank digest-pinned images.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
baseValuesNoExisting values.yaml to start from (optional)
targetLevelYesIL target level
enabledAddonsNoBig Bang addons to include e.g. ["istio","monitoring","logging","policy","vault","keycloak"]
clusterNameNo
registryUrlNoRegistry URL (default: registry1.dso.mil)

Implementation Reference

  • The handler function handleBigbangHarden that executes the tool logic. It validates args via Zod schema, calls Anthropic Claude API with the Big Bang hardening prompt, and returns the response text.
    export async function handleBigbangHarden(args: unknown): Promise<string> {
      return runTool('bigbang_harden', args, Schema, async ({ baseValues, targetLevel, enabledAddons, clusterName, registryUrl }) => {
        const response = await anthropic.messages.create({
          model: MODEL,
          max_tokens: getTokenBudget('bigbang_harden'),
          system: PLATFORM_ONE_SYSTEM,
          messages: [
            {
              role: 'user',
              content: `Generate a fully hardened Big Bang values.yaml for ${targetLevel}.
    
    **Cluster Name:** ${clusterName}
    **Registry:** ${registryUrl}
    **Enabled Addons:** ${(enabledAddons ?? ['istio', 'monitoring', 'logging', 'policy']).join(', ')}
    ${baseValues ? `\n**Base Values to Start From:**\n\`\`\`yaml\n${baseValues}\n\`\`\`` : ''}
    
    Provide:
    1. **Complete hardened values.yaml** with all security configurations
       - Iron Bank images from ${registryUrl} with SHA256 digest pins
       - Istio strict mTLS (PeerAuthentication STRICT mode)
       - OPA Gatekeeper / Kyverno policies enabled
       - NetworkPolicies restricting inter-namespace traffic
       - Resource limits on all workloads
       - Non-root containers enforced
       - Read-only root filesystems where possible
       - Secrets encryption at rest
    2. **Iron Bank Images Used** — table: Image | IB Path | Digest | Version
    3. **Required Kubernetes Secrets** to create before deployment (with creation commands)
    4. **Pre-deployment Checklist** (cluster requirements: node sizes, storage classes, etc.)
    5. **Post-deployment Verification Commands** to confirm ${targetLevel} compliance
    
    Use realistic Iron Bank registry paths and include actual STIG/IL requirements that drive each configuration.`,
            },
          ],
        });
    
        return response.content[0].type === 'text' ? response.content[0].text : '';
      });
    }
  • The tool definition (bigbangHardenTool) with name 'bigbang_harden', description, and JSON Schema input schema defining baseValues, targetLevel (il4/il5), enabledAddons, clusterName, and registryUrl.
    export const bigbangHardenTool = {
      name: 'bigbang_harden',
      description:
        'Generate a fully hardened Big Bang values.yaml targeting DoD IL4 or IL5 from scratch or from an existing values file. Includes Chainguard/Iron Bank digest-pinned images.',
      inputSchema: {
        type: 'object' as const,
        properties: {
          baseValues: { type: 'string', description: 'Existing values.yaml to start from (optional)' },
          targetLevel: { type: 'string', enum: ['il4', 'il5'], description: 'IL target level' },
          enabledAddons: {
            type: 'array',
            items: { type: 'string' },
            description: 'Big Bang addons to include e.g. ["istio","monitoring","logging","policy","vault","keycloak"]',
          },
          clusterName: { type: 'string' },
          registryUrl: {
            type: 'string',
            description: 'Registry URL (default: registry1.dso.mil)',
          },
        },
        required: ['targetLevel'],
      },
    };
  • Zod validation schema enforcing constraints: baseValues max 20000 chars, targetLevel enum (il4/il5), enabledAddons array max 50 items each max 500 chars (defaults to istio/monitoring/logging/policy), clusterName max 500 chars (default 'bb-cluster'), registryUrl max 500 chars (default 'registry1.dso.mil').
    const Schema = z.object({
      baseValues: z.string().max(20000).optional(),
      targetLevel: z.enum(['il4', 'il5']),
      enabledAddons: z.array(z.string().max(500)).max(50).default(['istio', 'monitoring', 'logging', 'policy']),
      clusterName: z.string().max(500).default('bb-cluster'),
      registryUrl: z.string().max(500).default('registry1.dso.mil'),
    });
  • Import of bigbangHardenTool and handleBigbangHarden from the implementation file.
    import { bigbangHardenTool, handleBigbangHarden } from './platform-one/bigbang-harden.js';
  • bigbangHardenTool registered in the allTools array for tool listing/discovery.
    bigbangHardenTool,
  • Routing: case 'bigbang_harden' in the switch statement maps to handleBigbangHarden(args).
    case 'bigbang_harden':        return handleBigbangHarden(args);
  • Token budget for bigbang_harden set to 8192 tokens.
    bigbang_harden: 8192,
  • Timeout for bigbang_harden set to 60000ms (60 seconds).
    bigbang_harden: 60000,
  • Minimum response length validation for bigbang_harden set to 500 characters.
    bigbang_harden: 500,
Behavior3/5

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

With no annotations, the description bears full transparency burden. It mentions generating or modifying a values file and including digest-pinned images, but omits side effects, permissions, or whether it overwrites files. Basic disclosure but not comprehensive.

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?

Two succinct sentences front-load the core purpose. No redundant information; every phrase serves a purpose.

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

Completeness4/5

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

Given 5 parameters, no output schema, and no annotations, the description covers the main function well. It explains generation, inputs, and output nature. Could detail what 'fully hardened' entails, but still mostly complete.

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 80% (4 of 5 parameters described). Description adds context linking 'from scratch' to baseValues and 'digest-pinned images' to registryUrl, but does not substantially enrich parameter meaning beyond schema.

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

Purpose5/5

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

Description clearly states the tool generates a fully hardened Big Bang values.yaml for DoD IL4/IL5, either from scratch or from an existing file. It distinguishes from sibling tools like bigbang_validate and addon_configurator by specifying the hardening focus.

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

Usage Guidelines3/5

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

Description implies use when needing a hardened values file for IL4/IL5, but does not explicitly state when to use versus alternatives or when not to use. No exclusion or alternative guidance is provided.

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