verify_before_acting — Second Opinion MCP Prompt

verify_before_acting is one of 2 prompts on the Second Opinion MCP server. Connect the server and it appears in your client, ready to invoke.

by client

How to invoke verify_before_acting from your client

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

Other prompts on this server

• adopt_verification_policy

Second Opinion also offers 1 resource — data you attach as context, where a prompt is something you run.

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.