OPENAI_API_KEY=your-openai-api-key-here ANTHROPIC_API_KEY=your-anthropic-api-key-here

# Using stdio transport (default) prompt-tester # Using SSE transport on custom port prompt-tester --transport sse --port 8000

{ "providers": { "openai": [ { "type": "gpt-4", "name": "gpt-4", "input_cost": 0.03, "output_cost": 0.06, "description": "Most capable GPT-4 model" }, // ... other models ... ], "anthropic": [ // ... models ... ] } }

{ "comparisons": [ { "provider": "openai", "model": "gpt-4", "system_prompt": "You are a helpful assistant.", "user_prompt": "Explain quantum computing in simple terms.", "temperature": 0.7 }, { "provider": "anthropic", "model": "claude-3-opus-20240229", "system_prompt": "You are a helpful assistant.", "user_prompt": "Explain quantum computing in simple terms.", "temperature": 0.7 } ] }

{ "mode": "start", "provider": "openai", "model": "gpt-4", "system_prompt": "You are a helpful assistant specializing in physics.", "user_prompt": "Can you explain what dark matter is?" }

{ "mode": "continue", "conversation_id": "conv_12345", "user_prompt": "How does that relate to dark energy?" }

import asyncio import json from mcp.client.session import ClientSession from mcp.client.stdio import StdioServerParameters, stdio_client async def main(): async with stdio_client( StdioServerParameters(command="prompt-tester") ) as (read, write): async with ClientSession(read, write) as session: await session.initialize() # 1. List available providers and models providers_result = await session.call_tool("list_providers", {}) print("Available providers and models:", providers_result) # 2. Run a basic test with a single model and prompt comparison_result = await session.call_tool("test_comparison", { "comparisons": [ { "provider": "openai", "model": "gpt-4", "system_prompt": "You are a helpful assistant.", "user_prompt": "Explain quantum computing in simple terms.", "temperature": 0.7, "max_tokens": 500 } ] }) print("Single model test result:", comparison_result) # 3. Compare multiple prompts/models side by side comparison_result = await session.call_tool("test_comparison", { "comparisons": [ { "provider": "openai", "model": "gpt-4", "system_prompt": "You are a helpful assistant.", "user_prompt": "Explain quantum computing in simple terms.", "temperature": 0.7 }, { "provider": "anthropic", "model": "claude-3-opus-20240229", "system_prompt": "You are a helpful assistant.", "user_prompt": "Explain quantum computing in simple terms.", "temperature": 0.7 } ] }) print("Comparison result:", comparison_result) # 4. Start a multi-turn conversation conversation_start = await session.call_tool("test_multiturn_conversation", { "mode": "start", "provider": "openai", "model": "gpt-4", "system_prompt": "You are a helpful assistant specializing in physics.", "user_prompt": "Can you explain what dark matter is?" }) print("Conversation started:", conversation_start) # Get the conversation ID from the response response_data = json.loads(conversation_start.text) conversation_id = response_data.get("conversation_id") # Continue the conversation if conversation_id: conversation_continue = await session.call_tool("test_multiturn_conversation", { "mode": "continue", "conversation_id": conversation_id, "user_prompt": "How does that relate to dark energy?" }) print("Conversation continued:", conversation_continue) # Get the conversation history conversation_history = await session.call_tool("test_multiturn_conversation", { "mode": "get", "conversation_id": conversation_id }) print("Conversation history:", conversation_history) asyncio.run(main())