Skip to main content
Glama
ai-naming-standard

AI Naming Standard MCP Server

Official

createProjectStructure

Generate standardized 8-folder project structures following v6 conventions for microservices architecture, including META directories for organized development workflows.

Instructions

Create v6 standard 8-folder project structure (includes 07_META)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
projectNameNoName of the new projectnew-project
versionNoConvention version (v5 or v6)v6

Implementation Reference

  • The primary handler function for the 'createProjectStructure' tool. It generates a standard project structure with 7 folders (00_DOCS to 06_LOGS), sample files with AI permission headers, mkdir commands, and structure metadata.
    export async function createProjectStructure({ projectName = 'new-project' }) {
      const msg = getMessages();
      const rules = namingRules();
      
      const structure = {
        projectName,
        folders: [],
        files: [],
        commands: []
      };
      
      // 7개 표준 폴더 생성 명령
      for (const [folderName, folderInfo] of Object.entries(rules.standardFolders)) {
        structure.folders.push({
          name: folderName,
          path: `${projectName}/${folderName}`,
          description: folderInfo.description,
          aiPermission: folderInfo.aiPermission
        });
        
        structure.commands.push(`mkdir ${projectName}/${folderName}`);
      }
      
      // 기본 파일 추가 (ChatGPT Enhancement: AI 권한 헤더 포함)
      structure.files = [
        { 
          path: `${projectName}/00_DOCS/README.md`, 
          content: `<!-- ⚠️ AI PERMISSION: NO-MODIFY -->\n<!-- This file is protected from AI modifications -->\n# ${projectName}\n\nBuilt with AI Naming Convention v5.0.1 (ChatGPT Enhanced)` 
        },
        { 
          path: `${projectName}/01_CONFIG/.env.example`, 
          content: '# ⚠️ AI PERMISSION: NO-MODIFY - CRITICAL\n# Environment variables\n# Manual changes only - contains sensitive data\n' 
        },
        { 
          path: `${projectName}/01_CONFIG/config.dev.yml`, 
          content: '# ⚠️ AI PERMISSION: NO-MODIFY\nenv: development\n' 
        },
        { path: `${projectName}/01_CONFIG/.gitignore`, content: '.env\nnode_modules/\n05_BUILD/\n06_LOGS/' },
        { path: `${projectName}/02_STATIC/ASSET_placeholder.txt`, content: '# Use ASSET_ prefix for all asset files' },
        { path: `${projectName}/02_STATIC/TEMPLATE_base.html`, content: '<!-- TEMPLATE_ prefix for templates -->' },
        { path: `${projectName}/02_STATIC/CONFIG_theme.json`, content: '{"theme":"default"}' },
        { path: `${projectName}/03_ACTIVE/.gitkeep`, content: '' },
        { path: `${projectName}/04_TEST/001_TEST_Main_Unit_COMMON.test.js`, content: '// Test file with indexed naming\n// [Deps]: 001\n' },
        { 
          path: `${projectName}/.ai_instructions.md`, 
          content: `# AI Development Instructions (v5.0.1 ChatGPT Enhanced)\n\n## ⚠️ Folder Permissions\n- 00_DOCS: NO-MODIFY\n- 01_CONFIG: NO-MODIFY - CRITICAL\n- 02_STATIC: Use ASSET_, TEMPLATE_, CONFIG_ prefixes\n- 03_ACTIVE: Full access (primary workspace)\n- 04_TEST: Use indexed naming (001_TEST_*)\n\n## [Deps] Dependency Markers\n- Sequential: 001-1, 001-2\n- Parallel: 001a, 001b\n- Subordinate: 001s1, 001s2\n- None: Entry point`
        }
      ];
      
      // 전체 생성 명령 (Windows/Unix)
      structure.createCommand = {
        windows: structure.commands.join(' && '),
        unix: structure.commands.join(' && ')
      };
      
      return {
        ...structure,
        message: msg.v5?.projectCreated || 'Project structure created with 7 standard folders'
      };
    }
  • The input schema definition for the tool, specifying parameters like projectName (default 'new-project') and optional version (v5/v6). Part of the TOOLS array used for MCP tool registration.
      name: 'createProjectStructure',
      description: 'Create v6 standard 8-folder project structure (includes 07_META)',
      inputSchema: {
        type: 'object',
        properties: {
          projectName: {
            type: 'string',
            description: 'Name of the new project',
            default: 'new-project'
          },
          version: {
            type: 'string',
            description: 'Convention version (v5 or v6)',
            enum: ['v5', 'v6'],
            default: 'v6'
          }
        }
      }
    },
  • src/index.js:624-625 (registration)
    Registration and dispatch of the tool in the MCP CallToolRequestSchema handler's switch statement, where tool calls are routed to the handler function.
    case 'createProjectStructure':
      result = await createProjectStructure(args);
  • src/index.js:584-586 (registration)
    MCP server registration for listing tools, which includes the createProjectStructure tool via the TOOLS() function.
    server.setRequestHandler(ListToolsRequestSchema, async () => {
      return { tools: TOOLS() };
    });
  • Import statement for the createProjectStructure handler from src/tools/index.js.
    createProjectStructure,
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool creates a structure, implying a write operation, but doesn't disclose critical details like whether it overwrites existing folders, requires specific permissions, has side effects, or how it handles errors. For a creation tool with zero annotation coverage, this lack of behavioral context is a significant gap.

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 ('Create v6 standard 8-folder project structure') and adds a useful detail ('includes 07_META') without any wasted words. It's appropriately sized for the tool's complexity, making it easy for an agent to parse quickly.

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?

Given the tool's moderate complexity (2 parameters, no output schema, no annotations), the description is minimally adequate. It covers the basic purpose but lacks usage guidelines, behavioral details, and output information. While it's complete enough to understand what the tool does at a high level, it doesn't provide sufficient context for safe and effective invocation without additional assumptions.

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%, so the schema already fully documents both parameters (projectName and version). The description adds no additional meaning beyond what the schema provides, such as explaining the significance of 'v6' or the '07_META' folder in relation to parameters. With high schema coverage, the baseline score of 3 is appropriate, as the description doesn't compensate but also doesn't detract.

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 ('Create') and the resource ('v6 standard 8-folder project structure'), including the specific detail that it includes '07_META'. It distinguishes this from siblings like 'createAIRoleMatrix' or 'getProjectTemplate' by focusing on folder structure creation rather than role matrices or template retrieval. However, it doesn't explicitly contrast with similar tools like 'suggestFolder' or 'migrateFromV4', which slightly limits differentiation.

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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, when not to use it, or compare it to siblings like 'migrateFromV4' (for version migration) or 'suggestFolder' (for folder suggestions). Without such context, an agent might struggle to choose this tool appropriately in scenarios where other tools could be more suitable.

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/ai-naming-standard/mcp'

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