GLM-4.6 MCP Server

Instructions

Implementation Reference

• src/glm-client.ts:159-174 (handler)

  Core handler function that formats a query for GLM-4.6 to review the technical decision based on provided decision and context, then calls the shared consultArchitecture method to get the AI response.
  async reviewTechnicalDecision(decision: string, context: string): Promise<string> { const query = `Review the following technical decision: Decision: ${decision} Context: ${context} Provide: 1. Architectural impact assessment 2. Trade-offs analysis 3. Alternative approaches 4. Risk evaluation 5. Recommendation with justification`; return this.consultArchitecture(query); }
• src/index.ts:82-95 (schema)

  Defines the input validation schema requiring 'decision' (string: the technical decision) and 'context' (string: surrounding architecture and constraints).
  inputSchema: { type: 'object', properties: { decision: { type: 'string', description: 'The technical decision to review', }, context: { type: 'string', description: 'Context including current architecture, constraints, and objectives', }, }, required: ['decision', 'context'], },
• src/index.ts:79-96 (registration)

  Tool registration in the MCP tools list, including name, description, and schema, returned by ListTools handler.
  { name: 'review_technical_decision', description: 'Review and evaluate a technical decision using GLM-4.6 architectural expertise. Assesses impact, trade-offs, alternatives, risks, and provides recommendations.', inputSchema: { type: 'object', properties: { decision: { type: 'string', description: 'The technical decision to review', }, context: { type: 'string', description: 'Context including current architecture, constraints, and objectives', }, }, required: ['decision', 'context'], }, },
• src/index.ts:185-196 (handler)

  MCP server dispatch handler for CallTool requests matching 'review_technical_decision', extracts arguments and invokes the GLMClient handler method.
  case 'review_technical_decision': { const { decision, context } = args as { decision: string; context: string }; const response = await glmClient.reviewTechnicalDecision(decision, context); return { content: [ { type: 'text', text: response, }, ], }; }