# hybrid-rag-mcp

> hybrid-rag-mcp — udarshmarthala-hybrid-rag-mcp. Use this tool when you need to efficiently search and retrieve relevant documents using a combination of traditional and dense vector retrieval methods, with advanced reranking and evaluation capabilities. It solves problems related to information retrieval, document search, and question answering by providing accurate and relevant results. Ideal for use cases requiring robust search functionality, such as knowledge graph querying or natural language processing applications.

Canonical page: https://skillsregistry.net/skills/udarshmarthala-hybrid-rag-mcp  
JSON: https://api.skillsregistry.net/v1/skills/udarshmarthala-hybrid-rag-mcp

## Description

An MCP server that provides a search_docs tool with hybrid retrieval (BM25 + dense vectors) and cross-encoder reranking, backed by evaluation, prompt-injection guardrails, and OpenTelemetry tracing.

## Trust

- **Trust score (0–1):** 0.68
- **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/m9xr0p8lp2)
- **Repository:** <https://github.com/udarshmarthala/hybrid-rag-mcp>

## 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": "udarshmarthala-hybrid-rag-mcp"
    }
  }
}
```

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