Skip to main content
Glama
kevinlin

Spec-driven Development MCP Server

by kevinlin

spec_coding_requirements_start

Initiate requirements collection for spec-driven development by providing structured guidance to gather feature specifications in EARS format.

Instructions

Start the requirements collection phase and provide guidance for requirements gathering

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
session_idYesSession identifier
feature_nameYesFeature name

Implementation Reference

  • The main handler function that executes the tool logic: logs the start, reads 'gen-requirement.md' template, and returns a formatted Markdown prompt for requirements gathering including workflow progress and instructions.
    export async function requirementsStart( params: RequirementsStartParams ): Promise<string> { const { session_id, feature_name } = params; console.error(`[MCP] Starting requirements collection for feature: ${feature_name}`); // Use gen-requirement.md template const template = await readTemplate('gen-requirement.md', { feature_name, session_id }); return `# 📋 Requirements Gathering Stage (2/5) ## Feature: ${feature_name} ### Workflow Progress: - [x] 1. Goal Collection ✅ - [x] 2. **Requirements Gathering** ← Current Stage - [ ] 3. Design Documentation - [ ] 4. Task Planning - [ ] 5. Task Execution --- ${template} --- **Important**: - Please generate requirements document according to the above guidelines - **Only when you explicitly confirm the requirements are complete can you call** \`spec_coding_requirements_confirmed\` tool - **Never** call the next stage tool before the user **explicitly confirms the requirements** **Session Information**: - Session ID: \`${session_id}\` - Feature Name: \`${feature_name}\``; }
  • Defines the tool's metadata including name, description, and input schema requiring session_id and feature_name.
    { name: 'spec_coding_requirements_start', description: 'Start the requirements collection phase and provide guidance for requirements gathering', inputSchema: { type: 'object', properties: { session_id: { type: 'string', description: 'Session identifier' }, feature_name: { type: 'string', description: 'Feature name' } }, required: ['session_id', 'feature_name'] }
  • src/server.ts:215-217 (registration)
    Registers the handler for the tool in the switch statement within the CallToolRequestSchema handler, delegating to the requirementsStart function.
    case 'spec_coding_requirements_start': result = await requirementsStart(args as any); break;
  • TypeScript interface defining the input parameters for the handler function, matching the tool's input schema.
    export interface RequirementsStartParams { session_id: string; feature_name: string; }

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/kevinlin/spec-coding-mcp'

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