Gemini MCP Server

Instructions

Implementation Reference

• src/enhanced-stdio-server.ts:504-616 (handler)

  The core handler function for the 'generate_text' tool. It processes input arguments, constructs a request to the Google Gemini API (using the genAI SDK), handles advanced features like JSON mode, grounding, system instructions, conversation history, and returns the generated text response.
  private async generateText(id: any, args: any): Promise<MCPResponse> { try { const model = args.model || 'gemini-2.5-flash'; const modelInfo = GEMINI_MODELS[model as keyof typeof GEMINI_MODELS]; if (!modelInfo) { throw new Error(`Unknown model: ${model}`); } // Build generation config const generationConfig: any = { temperature: args.temperature || 0.7, maxOutputTokens: args.maxTokens || 2048, topK: args.topK || 40, topP: args.topP || 0.95 }; // Add JSON mode if requested if (args.jsonMode) { generationConfig.responseMimeType = 'application/json'; if (args.jsonSchema) { generationConfig.responseSchema = args.jsonSchema; } } // Build the request const requestBody: any = { model, contents: [{ parts: [{ text: args.prompt }], role: 'user' }], generationConfig }; // Add system instruction if provided if (args.systemInstruction) { requestBody.systemInstruction = { parts: [{ text: args.systemInstruction }] }; } // Add safety settings if provided if (args.safetySettings) { requestBody.safetySettings = args.safetySettings; } // Add grounding if requested and supported if (args.grounding && modelInfo.features.includes('grounding')) { requestBody.tools = [{ googleSearch: {} }]; } // Handle conversation context if (args.conversationId) { const history = this.conversations.get(args.conversationId) || []; if (history.length > 0) { requestBody.contents = [...history, ...requestBody.contents]; } } // Call the API using the new SDK format const result = await this.genAI.models.generateContent({ model, ...requestBody }); const text = result.text || ''; // Update conversation history if needed if (args.conversationId) { const history = this.conversations.get(args.conversationId) || []; history.push(...requestBody.contents); history.push({ parts: [{ text: text }], role: 'model' }); this.conversations.set(args.conversationId, history); } return { jsonrpc: '2.0', id, result: { content: [{ type: 'text', text: text }], metadata: { model, tokensUsed: result.usageMetadata?.totalTokenCount, candidatesCount: result.candidates?.length || 1, finishReason: result.candidates?.[0]?.finishReason } } }; } catch (error) { console.error('Error in generateText:', error); return { jsonrpc: '2.0', id, error: { code: -32603, message: error instanceof Error ? error.message : 'Internal error' } }; }
• src/enhanced-stdio-server.ts:195-271 (schema)

  The input schema defining all parameters for the generate_text tool, including required prompt, optional model selection, generation parameters, advanced features like JSON mode and grounding.
  inputSchema: { type: 'object', properties: { prompt: { type: 'string', description: 'The prompt to send to Gemini' }, model: { type: 'string', description: 'Specific Gemini model to use', enum: Object.keys(GEMINI_MODELS), default: 'gemini-2.5-flash' }, systemInstruction: { type: 'string', description: 'System instruction to guide model behavior' }, temperature: { type: 'number', description: 'Temperature for generation (0-2)', default: 0.7, minimum: 0, maximum: 2 }, maxTokens: { type: 'number', description: 'Maximum tokens to generate', default: 2048 }, topK: { type: 'number', description: 'Top-k sampling parameter', default: 40 }, topP: { type: 'number', description: 'Top-p (nucleus) sampling parameter', default: 0.95 }, jsonMode: { type: 'boolean', description: 'Enable JSON mode for structured output', default: false }, jsonSchema: { type: 'object', description: 'JSON schema for structured output (when jsonMode is true)' }, grounding: { type: 'boolean', description: 'Enable Google Search grounding for up-to-date information', default: false }, safetySettings: { type: 'array', description: 'Safety settings for content filtering', items: { type: 'object', properties: { category: { type: 'string', enum: ['HARM_CATEGORY_HARASSMENT', 'HARM_CATEGORY_HATE_SPEECH', 'HARM_CATEGORY_SEXUALLY_EXPLICIT', 'HARM_CATEGORY_DANGEROUS_CONTENT'] }, threshold: { type: 'string', enum: ['BLOCK_NONE', 'BLOCK_ONLY_HIGH', 'BLOCK_MEDIUM_AND_ABOVE', 'BLOCK_LOW_AND_ABOVE'] } } } }, conversationId: { type: 'string', description: 'ID for maintaining conversation context' } }, required: ['prompt'] }
• src/enhanced-stdio-server.ts:474-475 (registration)

  Dispatch/registration in handleToolCall switch statement that routes 'generate_text' calls to the generateText handler.
  case 'generate_text': return await this.generateText(request.id, args);
• src/enhanced-stdio-server.ts:192-272 (registration)

  Tool registration object returned by getAvailableTools(), including name, description, and inputSchema for tools/list endpoint.
  { name: 'generate_text', description: 'Generate text using Google Gemini with advanced features', inputSchema: { type: 'object', properties: { prompt: { type: 'string', description: 'The prompt to send to Gemini' }, model: { type: 'string', description: 'Specific Gemini model to use', enum: Object.keys(GEMINI_MODELS), default: 'gemini-2.5-flash' }, systemInstruction: { type: 'string', description: 'System instruction to guide model behavior' }, temperature: { type: 'number', description: 'Temperature for generation (0-2)', default: 0.7, minimum: 0, maximum: 2 }, maxTokens: { type: 'number', description: 'Maximum tokens to generate', default: 2048 }, topK: { type: 'number', description: 'Top-k sampling parameter', default: 40 }, topP: { type: 'number', description: 'Top-p (nucleus) sampling parameter', default: 0.95 }, jsonMode: { type: 'boolean', description: 'Enable JSON mode for structured output', default: false }, jsonSchema: { type: 'object', description: 'JSON schema for structured output (when jsonMode is true)' }, grounding: { type: 'boolean', description: 'Enable Google Search grounding for up-to-date information', default: false }, safetySettings: { type: 'array', description: 'Safety settings for content filtering', items: { type: 'object', properties: { category: { type: 'string', enum: ['HARM_CATEGORY_HARASSMENT', 'HARM_CATEGORY_HATE_SPEECH', 'HARM_CATEGORY_SEXUALLY_EXPLICIT', 'HARM_CATEGORY_DANGEROUS_CONTENT'] }, threshold: { type: 'string', enum: ['BLOCK_NONE', 'BLOCK_ONLY_HIGH', 'BLOCK_MEDIUM_AND_ABOVE', 'BLOCK_LOW_AND_ABOVE'] } } } }, conversationId: { type: 'string', description: 'ID for maintaining conversation context' } }, required: ['prompt'] } },