is_now_dangerous — Seiche — world-markets evidence terminal MCP Prompt

is_now_dangerous is one of 4 prompts on the Seiche — world-markets evidence terminal MCP server. Connect the server and it appears in your client, ready to invoke.

by client

How to invoke is_now_dangerous from your client

• Claude Code Seiche — world-markets evidence terminal Prompt/is_now_dangerous run in your project directory
• Claude Desktop Seiche — world-markets evidence terminal Prompt/is_now_dangerous ~/Library/Application Support/Claude/claude_desktop_config.json
• Cursor Seiche — world-markets evidence terminal Prompt/is_now_dangerous ~/.cursor/mcp.json
• VS Code Seiche — world-markets evidence terminal Prompt/is_now_dangerous .vscode/mcp.json
• Zed Seiche — world-markets evidence terminal Prompt/is_now_dangerous ~/.config/zed/settings.json
• Windsurf Seiche — world-markets evidence terminal Prompt/is_now_dangerous ~/.codeium/windsurf/mcp_config.json
• Cline Seiche — world-markets evidence terminal Prompt/is_now_dangerous ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
• Gemini CLI Seiche — world-markets evidence terminal Prompt/is_now_dangerous ~/.gemini/settings.json
• Grok Seiche — world-markets evidence terminal Prompt/is_now_dangerous .mcp.json (in your project root)
• ChatGPT Seiche — world-markets evidence terminal Prompt/is_now_dangerous Settings → Connectors → Advanced → Developer mode
• Claude.ai Seiche — world-markets evidence terminal Prompt/is_now_dangerous Settings → Connectors → Add custom connector
• LangChain Seiche — world-markets evidence terminal Prompt/is_now_dangerous pip install langchain-mcp-adapters

Other prompts on this server

• money_market_deep_dive
• world_markets_briefing
• cross_market_cash_pressure

Read from the server itself, by connecting to it and calling prompts/list on 24 September 2026. A listing does not declare its prompts, so asking is the only way to know them, and this is what the server actually offers rather than what its listing claims. Names only are stored; connect the server for each prompt's arguments.