setup

Configure a modular RAG MCP server with provider selection and startup recovery.

Updated Apr 1, 2026
One-click install
npx skills add https://github.com/zhuangfanupup/modular-rag-mcp-server --skill setup-zhuangfanupup
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: setup
Source: https://github.com/zhuangfanupup/modular-rag-mcp-server/tree/main/.github/skills/setup
Command: npx skills add https://github.com/zhuangfanupup/modular-rag-mcp-server --skill setup-zhuangfanupup

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the friction of setting up a modular RAG MCP server from scratch by guiding the user through provider choice, credential entry, configuration generation, dependency installation, validation, and launch.

Core Features & Use Cases

  • Provider Selection: Choose the right LLM, embedding, vision, and rerank providers for the target deployment.
  • Config Generation: Build a complete settings file with the correct models, endpoints, dimensions, and feature flags.
  • Startup Recovery: Diagnose common launch problems, install missing packages, and retry fixes automatically.
  • Use Case: A new user can go from a clean clone to a working dashboard and MCP server without manually assembling configuration details.

Quick Start

Ask this Skill to configure a fresh checkout, generate the settings file, install the required dependencies, and start the dashboard.

Frequently Asked Questions about setup

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure a RAG MCP server for first-run deployment?

Configuring a RAG MCP server involves selecting providers, collecting credentials, synthesizing YAML settings, and installing dependencies. This setup validates the configuration and launches the dashboard for operational startup without manual assembly.

What LLM and embedding providers can I choose when scaffolding a RAG server?

When scaffolding a RAG server, you can choose from OpenAI, Azure OpenAI, DeepSeek, Ollama, Qwen, and Gemini providers. The setup supports selecting LLM, embedding, vision, and rerank providers to match your target deployment requirements.

How do I fix RAG server launch failures and missing dependencies?

Fixing RAG server launch failures uses automated startup recovery to diagnose problems, install missing packages, and validate configurations. The setup runs up to three retry rounds to ensure a successful deployment.

Does the RAG setup process support generating configuration for unsupported integrations?

Yes, the RAG setup process supports unsupported integrations via provider-aware scaffolding. It synthesizes YAML-based settings with correct models, endpoints, and feature flags for custom provider workflows.

What is the best way to go from a clean clone to a working RAG dashboard?

Going from a clean clone to a working RAG dashboard requires automated directory preparation, import checks, and config generation. This setup launches the dashboard and MCP server without manually assembling configuration details.