# Hybrid RAG Project MCP Server

> Use this tool when you need to perform efficient and private document querying across multiple file formats, combining semantic search and keyword matching for optimal context recovery. It solves problems of information retrieval and document search, providing accurate results through a combination of semantic vector retrieval and BM25 keyword matching. Ideal for use cases where local document search is required, with inputs including PDF, CSV, and Markdown files, and outputs of relevant search results.

Canonical page: https://skillsregistry.net/skills/gwyer-hybrid-rag-project  
JSON: https://api.skillsregistry.net/v1/skills/gwyer-hybrid-rag-project

## Description

Enables Claude to perform hybrid search across local documents by combining semantic vector retrieval and BM25 keyword matching for optimal context recovery. It supports multiple file formats including PDF, CSV, and Markdown, leveraging local Ollama models for private and efficient document querying.

## Trust

- **Trust score (0–1):** 0.90
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/gag89lfuny)
- **Repository:** <https://github.com/gwyer/hybrid-rag-project>

## 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": "gwyer-hybrid-rag-project"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/gwyer-hybrid-rag-project` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/gwyer-hybrid-rag-project/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