use_prompt — mcp MCP Prompt
use_prompt
is one of 1 prompt on the
mcp
MCP server. Connect the server and it appears in your client, ready to invoke.
by client
How to invoke use_prompt from your client
- Claude Code mcp Prompt/use_prompt run in your project directory
- Claude Desktop mcp Prompt/use_prompt ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor mcp Prompt/use_prompt ~/.cursor/mcp.json
- VS Code mcp Prompt/use_prompt .vscode/mcp.json
- Zed mcp Prompt/use_prompt ~/.config/zed/settings.json
- Windsurf mcp Prompt/use_prompt ~/.codeium/windsurf/mcp_config.json
- Cline mcp Prompt/use_prompt ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI mcp Prompt/use_prompt ~/.gemini/settings.json
- Grok mcp Prompt/use_prompt .mcp.json (in your project root)
- ChatGPT mcp Prompt/use_prompt Settings → Connectors → Advanced → Developer mode
- Claude.ai mcp Prompt/use_prompt Settings → Connectors → Add custom connector
- LangChain mcp Prompt/use_prompt pip install langchain-mcp-adapters
mcp also offers 2 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.