research_plan — pubmed mcp server MCP Prompt

research_plan is one of 1 prompt on the pubmed mcp server MCP server. Connect the server and it appears in your client, ready to invoke.

by client

How to invoke research_plan from your client

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

pubmed mcp server 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.