Skip to main content
Glama
deenesjakoruzh
Ripnrip

qdrant-mcp-server

by Ripnrip
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

qdrant-mcp-server（维护中的复刻）

本复刻源自已废弃的 PyPI 包 qdrant-mcp-server 0.1.0（作者：fiyen；上游 github.com/fiyen/qdrant-mcp-server 已 404——不存在可提交 PR 的仓库）。

为什么会有这个复刻

原版会在 __init__ 中立即加载 sentence-transformers/all-MiniLM-L6-v2 模型。由于是 stdio MCP 服务器，每个 agent 运行时/会话都会生成自己的副本，因此 N 个空闲会话会占用 N × 约 1.35 GB 的重复模型内存（实测：5 个副本 = 5.7 GB）。另请参阅通用的“stdio trap”说明。

Related MCP server: Qdrant MCP Server

相对 PyPI 0.1.0 的改动

  • 懒加载补丁：嵌入模型改为在首次调用 generate_embedding 时才加载，而不是在启动时加载。空闲副本仅占用约 30 MB 内存。（仓库根目录中的 lazy-load.patch 就是参考用的 diff。）

安装（替代 PyPI 安装）

uv tool install --force git+https://github.com/Ripnrip/qdrant-mcp-server

这样，已有的 MCP 配置（command = /Users/admin/.local/bin/qdrant-mcp-server）可继续生效，今后的 uvx tool upgrade 也会从本复刻拉取更新，而不是从已废弃的 PyPI 0.1.0。

任何重装之后，需要重启正在运行的 qdrant-mcp-server 实例（Swift Reaper LaunchAgent 负责清理孤儿进程：com.local.qdrant-mcp-reaper）。

上下文：HAB-354 · ~/Documents/Developer/qdrant-mcp-ram-fix-2026-08-24/

This server cannot be installed

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd
A
license - permissive license
Not graded
quality - not tested
C
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • Qdrant MCP Server

    andrewlwn77
    A
    license
    Not graded
    quality
    D
    maintenance
    Provides semantic memory capabilities using Qdrant vector database with configurable embedding providers, allowing storage and retrieval of information using vector similarity.
    2
    Apache 2.0

  • Qdrant MCP Server

    mhalder
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables semantic search and document management using a local Qdrant vector database with OpenAI embeddings. Supports natural language queries, metadata filtering, and collection management for AI-powered document retrieval.
    164
    36
    MIT

  • Qdrant MCP Server

    mcandiav
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables storing and retrieving information using semantic search with Qdrant vector database. Acts as a memory layer for LLMs to persistently store and semantically search through information and metadata.
    Apache 2.0

View all related MCP servers

Related MCP Connectors

  • Ragora

    Search your knowledge bases from any AI assistant using hybrid RAG.

  • Amber

    Long-term memory for AI assistants. Hybrid retrieval, query expansion, auto-topics.

  • agentbay-mcp

    Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Ripnrip/qdrant-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server