{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_w9j6pm5q2weq","handle":"qdrant-mcp-server","url":"https://wellknown.network/agents/qdrant-mcp-server","links":{"self":"https://wellknown.network/agents/qdrant-mcp-server/record.json","html":"https://wellknown.network/agents/qdrant-mcp-server","markdown":"https://wellknown.network/agents/qdrant-mcp-server/record.md","api":"https://wellknown.network/api/v1/agents/qdrant-mcp-server","status":"https://wellknown.network/api/v1/agents/qdrant-mcp-server/status","claim":"https://wellknown.network/agents/qdrant-mcp-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/qdrant-mcp-server/claim.json","badge":"https://wellknown.network/agents/qdrant-mcp-server/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:qdrant-mcp-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"qdrant-mcp-server","summary":"A Model Context Protocol (MCP) server for Qdrant vector database with semantic search capabilities","description":"# Qdrant MCP Server \n \n[![PyPI version](https://badge.fury.io/py/qdrant-mcp-server.svg)](https://badge.fury.io/py/qdrant-mcp-server) \n[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/) \n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) \n \n一个基于 [Qdrant](https://qdrant.tech/) 向量数据库的 [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) 服务器，提供强大的语义搜索和知识管理功能。 \n \n## ✨ 特性 \n \n- 🚀 **即插即用**: 使用 `uvx` 一键运行，无需复杂配置 \n- 🔍 **语义搜索**: 基于向量相似度的智能搜索 \n- 🧠 **多种嵌入模型**: 支持本地 Sentence-Transformers 和在线 Jina AI \n- 📝 **完整 CRUD**: 创建、读取、更新、删除知识条目 \n- 🔧 **灵活配置**: 通过环境变量自定义各项参数 \n- 🌐 **标准协议**: 完全符合 MCP 规范 \n \n## 📦 安装 \n \n### 使用 uvx (推荐) \n \n最简单的方式是使用 `uvx` 直接运行: \n \n```bash \nuvx qdrant-mcp-server \n``` \n \n### 使用 uv \n \n```bash \nuv pip install qdrant-mcp-server \n``` \n \n### 使用 pip \n \n```bash \npip install qdrant-mcp-server \n``` \n \n## 🚀 快速开始 \n \n### 1. 配置环境变量 \n \n创建 `.env` 文件或设置环境变量: \n \n```bash \n# Qdrant 连接配置 \nQDRANT_URL=https://your-qdrant-instance.com:443 \nQDRANT_API_KEY=your-api-key-here \nCOLLECTION_NAME=my_knowledge_base \n \n# 嵌入模型配置 (二选一) \n# 选项1: 使用本地模型 (默认) \nEMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2 \nVECTOR_NAME=fast-all-minilm-l6-v2 \n \n# 选项2: 使用 Jina AI 在线模型 \n# EMBEDDING_MODEL=jina-embeddings-v3 \n# JINA_TOKEN=your-jina-api-key \n# VECTOR_NAME=jina-embeddings-v3 \n``` \n \n### 2. 在 MCP 客户端中配置 \n \n#### Claude Desktop 配置 \n \n编辑 `~/Library/Application Support/Claude/claude_desktop_config.json`: \n \n```json \n{ \n  \"mcpServers\": { \n    \"qdrant\": { \n      \"command\": \"uvx\", \n      \"args\": [\"qdrant-mcp-server\"], \n      \"env\": { \n        \"QDRANT_URL\": \"https://your-instance.com:443\", \n        \"QDRANT_API_KEY\": \"your-api-key\", \n        \"COLLECTION_NAME\": \"knowledge_base\" \n      } \n    } \n  } \n} \n``` \n \n#### Roo Code / OpenCode 配置 \n \n编辑配置文件 (如 `~/.config/opencode/opencode.json`): \n \n```json \n{ \n  \"mcp\": { \n    \"qdrant\": { \n      \"type\": \"local\", \n      \"command\": [\"uvx\", \"qdrant-m…","publisher":null,"homepage":"https://github.com/fiyen/qdrant-mcp-server#readme","repository":"https://github.com/fiyen/qdrant-mcp-server/issues","version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp","qdrant","vector-database","semantic-search","embeddings","ai"],"pricing":null,"endpoints":[{"url":"pypi:qdrant-mcp-server","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"data.database","name":"Databases","confidence":1,"provenance":"derived"},{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"}],"categories":["data"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"qdrant-mcp-server","registry":"pypi","observedAt":"2026-09-10T10:25:55.442Z","publishedAt":"2026-02-03T11:48:34.457983Z","latestVersion":"0.1.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"qdrant-mcp-server","url":"https://pypi.org/project/qdrant-mcp-server/","firstSeenAt":"2026-09-10T10:24:57.359Z","fetchedAt":"2026-09-10T10:24:57.359Z","normalizedAt":"2026-09-10T10:24:57.359Z"}]},"firstSeenAt":"2026-09-10T10:24:57.359Z","updatedAt":"2026-09-10T10:25:55.442Z"}