# rag-mcp-server

> rag-mcp-server — zhengzhi132-rag-mcp-server. Use this tool when you need to retrieve accurate answers to questions about PyTorch documentation, leveraging hybrid search and source-cited responses. It solves problems of information retrieval and question answering by providing relevant results from trusted sources. The tool takes in natural language queries as input and outputs precise answers with citations, making it ideal for developers and researchers seeking reliable information.

Canonical page: https://skillsregistry.net/skills/zhengzhi132-rag-mcp-server  
JSON: https://api.skillsregistry.net/v1/skills/zhengzhi132-rag-mcp-server

## Description

A RAG MCP server that enables retrieval-augmented question answering over PyTorch documentation, with hybrid search (FAISS+Chroma, BM25) and source-cited responses from DeepSeek.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/bubnxj75nc)
- **Repository:** <https://github.com/zhengzhi132/rag-mcp-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "zhengzhi132-rag-mcp-server"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zhengzhi132-rag-mcp-server` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zhengzhi132-rag-mcp-server/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt