recover_mcp_auth — agentView MCP Prompt

recover_mcp_auth is one of 4 prompts on the agentView MCP server. Connect the server and it appears in your client, ready to invoke.

by client

How to invoke recover_mcp_auth from your client

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

Other prompts on this server

• onboard_first_display
• asset_workflow
• render_premium_display_html

agentView also offers 15 resources — 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.