Skip to main content
Glama
Better Qdrant MCP Server

Better Qdrant MCP Server

by wrediam

더 나은 Qdrant MCP 서버

향상된 Qdrant 벡터 데이터베이스 기능을 위한 모델 컨텍스트 프로토콜(MCP) 서버입니다. 이 서버는 Qdrant 컬렉션 관리, 문서 추가 및 의미 검색을 위한 도구를 제공합니다.

특징

  • 컬렉션 목록 : 사용 가능한 모든 Qdrant 컬렉션 보기

  • 문서 추가 : 다양한 임베딩 서비스를 사용하여 Qdrant 컬렉션에 문서를 처리하고 추가합니다.

  • 검색 : 벡터 데이터베이스에서 의미 검색을 수행합니다.

  • 컬렉션 삭제 : Qdrant 데이터베이스에서 컬렉션을 제거합니다.

Related MCP server: doc-lib-mcp

설치

지엑스피1

또는 npx와 함께 직접 사용하세요:

npx better-qdrant-mcp-server

구성

서버는 구성에 환경 변수를 사용합니다. 프로젝트 루트의 .env 파일에서 환경 변수를 설정할 수 있습니다.

# Qdrant Configuration
QDRANT_URL=http://localhost:6333
QDRANT_API_KEY=your_api_key_if_needed

# Embedding Service API Keys
OPENAI_API_KEY=your_openai_api_key
OPENROUTER_API_KEY=your_openrouter_api_key
OLLAMA_ENDPOINT=http://localhost:11434

지원되는 임베딩 서비스

  • OpenAI : API 키가 필요합니다

  • OpenRouter : API 키가 필요합니다

  • Ollama : 로컬 임베딩 모델(기본 엔드포인트: http://localhost:11434 )

  • FastEmbed : 로컬 임베딩 모델

Claude와 함께 사용

Claude와 함께 이 MCP 서버를 사용하려면 MCP 설정 구성 파일에 추가하세요.

{
  "mcpServers": {
    "better-qdrant": {
      "command": "npx",
      "args": ["better-qdrant-mcp-server"],
      "env": {
        "QDRANT_URL": "http://localhost:6333",
        "QDRANT_API_KEY": "your_api_key_if_needed",
        "DEFAULT_EMBEDDING_SERVICE": "ollama",
        "OPENAI_API_KEY": "your_openai_api_key",
        "OPENAI_ENDPOINT": "https://api.openai.com/v1",
        "OPENROUTER_API_KEY": "your_openrouter_api_key",
        "OPENROUTER_ENDPOINT": "https://api.openrouter.com/v1",
        "OLLAMA_ENDPOINT": "http://localhost:11434",
        "OLLAMA_MODEL": "nomic-embed-text"
      }
    }
  }
}

예제 명령

컬렉션 목록

use_mcp_tool
server_name: better-qdrant
tool_name: list_collections
arguments: {}

문서 추가

use_mcp_tool
server_name: better-qdrant
tool_name: add_documents
arguments: {
  "filePath": "/path/to/your/document.pdf",
  "collection": "my-collection",
  "embeddingService": "openai",
  "chunkSize": 1000,
  "chunkOverlap": 200
}

찾다

use_mcp_tool
server_name: better-qdrant
tool_name: search
arguments: {
  "query": "your search query",
  "collection": "my-collection",
  "embeddingService": "openai",
  "limit": 5
}

컬렉션 삭제

use_mcp_tool
server_name: better-qdrant
tool_name: delete_collection
arguments: {
  "collection": "my-collection"
}

요구 사항

  • 노드.js >= 18.0.0

  • 실행 중인 Qdrant 서버(로컬 또는 원격)

  • 사용하려는 임베딩 서비스에 대한 API 키

특허

MIT

Available Tools

4 tools
add_documentsC

Add documents to a Qdrant collection with specified embedding service

Inputs: collection (required), embeddingService (required), filePath (required), chunkOverlap, +1 more.

delete_collectionC

Delete a Qdrant collection

Inputs: collection (required).

list_collectionsB

List all available Qdrant collections

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: add_documents handles document insertion, delete_collection removes collections, list_collections enumerates them, and search performs similarity queries. There is no overlap in functionality, making tool selection straightforward.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern (add_documents, delete_collection, list_collections, search). The naming is uniform and predictable, with no deviations in style or convention.

    Tool Count3/5

    With only 4 tools, the set feels thin for a vector database server, lacking operations like collection creation, document updates, or deletion. While the tools cover basic CRUD aspects, the scope is limited and may require workarounds for full functionality.

    Completeness2/5

    There are significant gaps in the tool surface for a Qdrant server: no create_collection tool, no update or delete document operations, and no management of embeddings or configurations. This incomplete coverage will likely cause agent failures in common workflows.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol (MCP) server that enables semantic search and retrieval of documentation using a vector database (Qdrant). This server allows you to add documentation from URLs or local files and then search through them using natural language queries.
      135
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol (MCP) server for Retrieval-Augmented Generation (RAG) operations. It provides tools for building and querying vector-based knowledge bases from document collections, enabling semantic search and document retrieval capabilities.
      15 PyPI
      3
      MIT