setup

Guides interactive setup of the enterprise modular RAG MCP project from a clean clone.

Updated Mar 9, 2026
One-click install
npx skills add https://github.com/zhunikaixin297/Enterprise-Modular-RAG-MCP --skill setup-zhunikaixin297
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: setup
Source: https://github.com/zhunikaixin297/Enterprise-Modular-RAG-MCP/tree/main/.github/skills/setup
Command: npx skills add https://github.com/zhunikaixin297/Enterprise-Modular-RAG-MCP --skill setup-zhunikaixin297

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the friction of getting a new Enterprise Modular RAG MCP environment running by guiding users through provider choice, credentials, dependency setup, configuration generation, and first launch.

Core Features & Use Cases

  • Interactive setup wizard: Collects the right LLM, embedding, vision, and rerank choices for a fresh project.
  • Configuration generation: Produces a valid settings file from provider-specific templates and model requirements.
  • Startup repair: Diagnoses setup failures, installs missing dependencies, and retries with guardrails.
  • Provider scaffolding: Creates boilerplate support for unimplemented OpenAI-compatible providers when needed.
  • Use case: A teammate clones the repository and wants a working dashboard and MCP server without manually reading every config detail.

Quick Start

Use the setup skill to configure providers, generate the project settings, install dependencies, validate the environment, and launch the dashboard from a clean clone.

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 project from a clean clone?

To configure a RAG MCP project from a clean clone, an interactive setup wizard guides you through provider selection, credential collection, config generation, dependency installation, validation, and dashboard launch in one flow.

What is the best way to set up OpenAI-compatible providers like DeepSeek or Ollama?

Setting up OpenAI-compatible providers like DeepSeek or Ollama involves an interactive wizard that collects provider-specific credentials, generates schema-aware configuration templates, and scaffolds boilerplate support for unimplemented stacks.

Can I use this setup wizard to configure Azure, Gemini, and Qwen simultaneously?

Yes, the setup wizard supports configuring multiple providers simultaneously, including Azure, Gemini, and Qwen, by collecting the appropriate LLM, embedding, vision, and rerank choices to produce a valid settings file.

How do I fix startup validation failures during MCP environment configuration?

To fix startup validation failures during MCP environment configuration, the setup process diagnoses setup errors, installs missing dependencies, and automatically retries with guardrails using a repair mechanism.

Does the setup process generate configuration files automatically for all selected LLM providers?

Yes, the setup process automatically generates a valid configuration file from provider-specific templates and model requirements after you select your desired LLM, embedding, vision, and rerank providers.