The brainstorm-mcp server orchestrates debates between multiple AI models, providing structured synthesis of their responses. It supports both hosted and API modes for multi-model brainstorming and code review.
From the registry: Multi-model AI brainstorming debates with code review and quick perspectives

Please install the `brainstorm-mcp` MCP server into my current AI client (that's you).
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","brainstorm-mcp"]
- optional environment variables:
- `OPENAI_API_KEY`: OpenAI API key (API mode) (example: `sk-<placeholder>`)
- `GEMINI_API_KEY`: Gemini API key (API mode) (example: `AIza<placeholder>`)
- `DEEPSEEK_API_KEY`: DeepSeek API key (API mode) (example: `sk-<placeholder>`)
- `BRAINSTORM_CONFIG`: Path to full provider config JSON (example: `/path/to/brainstorm.json`)
Note: Hosted mode needs no API keys; API mode uses env vars for provider keys.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.OPENAI_API_KEYrequiredAPI key for OpenAI model accessGEMINI_API_KEYrequiredAPI key for Gemini model accessDEEPSEEK_API_KEYrequiredAPI key for DeepSeek model accessAI Agents Framework with Self Reflection and MCP support