draft_feature_request — agent door MCP Prompt

draft_feature_request is one of 3 prompts on the agent door MCP server. Connect the server and it appears in your client, ready to invoke.

by client

How to invoke draft_feature_request from your client

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

Other prompts on this server

• price_my_crew
• compare_to_my_stack

agent door also offers 7 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.