# Knowledge Base MCP Server (Qdrant)

> Use this tool when you need to efficiently retrieve relevant documents from a large knowledge base, leveraging hybrid search capabilities that combine semantic and keyword retrieval. It solves problems related to information retrieval, document querying, and data fetching, particularly in applications like ChatGPT Deep Research. The tool accepts query inputs and returns relevant document outputs, making it ideal for use cases where accurate and speedy information retrieval is crucial.

Canonical page: https://skillsregistry.net/skills/devanshtb-mcp-poc-kc  
JSON: https://api.skillsregistry.net/v1/skills/devanshtb-mcp-poc-kc

## Description

Read-only MCP server with hybrid search combining dense semantic and sparse keyword retrieval via Qdrant, enabling document querying and fetching for ChatGPT Deep Research.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/apfqndfo4c)
- **Repository:** <https://github.com/devanshtb/mcp-poc-kc>

## 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": "devanshtb-mcp-poc-kc"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/devanshtb-mcp-poc-kc` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/devanshtb-mcp-poc-kc/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