# modular-rag-mcp-server

This skill guides the deployment and configuration of a modular RAG system exposed to assistants through MCP. Use it when connecting an assistant to a document knowledge base.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 199 installs · ★ 9 repo stars
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/mcp-skills/tree/HEAD/skills/modular-rag-mcp-server/SKILL.md
- Updated: 2026-10-09
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/modular-rag-mcp-server

## What it does

The skill covers a RAG workflow for adding documents to a knowledge base, retrieving results with semantic and exact-match search, and connecting the system to an assistant over MCP. The server provides tools to query the hub, list collections, and get a document summary. The project also includes a Streamlit dashboard and Ragas-based evaluation.

Models, embedding providers, rerankers, text splitters, and vector stores can be selected through configuration. Deployment requires Python 3.9+ and API keys for the providers you choose, such as OpenAI, Anthropic, or Cohere. A missing key for a selected provider will prevent that integration from working.

Install the skill with `npx skills add reason-machines/mcp-skills --skill modular-rag-mcp-server -a claude-code`. It provides setup guidance; building the RAG project itself involves creating a virtual environment, installing dependencies, and configuring `.env`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill modular-rag-mcp-server -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/modular-rag-mcp-server/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/modular-rag-mcp-server/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill modular-rag-mcp-server -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/modular-rag-mcp-server/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill modular-rag-mcp-server -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/modular-rag-mcp-server/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/mcp-skills skills/modular-rag-mcp-server
```

2. **Manually: put the files in place**
- File: `.github/skills/modular-rag-mcp-server/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill modular-rag-mcp-server -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/mcp-skills --path skills/modular-rag-mcp-server
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/modular-rag-mcp-server/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill modular-rag-mcp-server -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/mcp-skills/tree/HEAD/skills/modular-rag-mcp-server/SKILL.md

## When to use it
- connect an MCP server to an assistant
- ingest a PDF into a knowledge base
- retrieve documents with hybrid search
- configure an embedding provider or reranker
- evaluate RAG results with Ragas

## Example prompts
- Help me configure the modular RAG system and connect it to Claude Code through MCP.
- Explain how to ingest a PDF into the knowledge base and search its contents.
- Show me how to choose an embedding provider and evaluate retrieval with Ragas.

## Similar
- [rag-infrastructure](https://affpapa.org/en/nevibecode/skills/rag-infrastructure.md) — skill · 360 installs
- [rag-eval](https://affpapa.org/en/nevibecode/skills/rag-eval.md) — skill · 2500 installs
- [rag-observability-evals](https://affpapa.org/en/nevibecode/skills/rag-observability-evals.md) — skill · 353 installs
- [langchain-rag](https://affpapa.org/en/nevibecode/skills/langchain-rag.md) — skill · 18600 installs
- [qdrant-search-quality](https://affpapa.org/en/nevibecode/skills/qdrant-qdrant-search-quality.md) — skill · 1900 installs
- [rag](https://affpapa.org/en/nevibecode/skills/rag.md) — skill · 3900 installs

From the same set: [reason-machines/mcp-skills](https://affpapa.org/en/nevibecode/by/reason-machines/mcp-skills.md) — 98 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
