Qdrant MCP server

Qdrant MCP

<!-- mcp-name: io.github.avaazquezz/mcp-qdrant -->

A Model Context Protocol (MCP) server that exposes the full Qdrant vector database API as tools — collection management, advanced hybrid search, payload and vector editing, snapshots, and server observability. Not just store/find.

Table of Contents

• Overview
• Key Features
• Requirements
• Installation
• PyPI
• Docker
• Claude Desktop bundle (.mcpb)
• Quick Start
• Connecting to Claude
• Claude Desktop / Claude Code (local, stdio)
• Remote (streamable-http)
• Bring your own Qdrant (QDRANTMCPBYO)

Overview

Qdrant MCP is a thin MCP server that wraps the Qdrant API one-to-one: it registers a tool per Qdrant operation, validates the input with Pydantic, calls the official qdrant-client SDK, and returns the result. It never generates embeddings, never parses documents, and never decides how to chunk text — it is not a RAG system, on purpose. Whatever an LLM client wants to store or query, it brings its own vectors.

That focus is also what sets it apart from the official Qdrant MCP server, which exposes exactly two tools (store/find) and does embed documents for you. This server covers the rest of Qdrant's surface — everything under collections, points, search, payload, indexing, snapshots, and observability — so an LLM client can manage a Qdrant deployment end to end, not just push and pull memories through a narrow interface.

See ROADMAP.md for the full phase-by-phase design history, including every finding that shaped a decision (in Spanish).

Key Features

scrolling, counting.

• Full collection & point lifecycle — create/update/delete collections, CRUD on points,

prefetch stages), grouped queries, recommend, discover, and pairwise distance matrices.

• Every Qdrant search mode — plain vector search, hybrid search (RRF/DBSF fusion with

counting, named (dense/sparse) vector management, atomic batch operations.

• Payload & vector editing — set/overwrite/delete/clear payload, payload indexes, facet

issues.

• Snapshots — per-collection and full-storage backup/restore.
• Observability — telemetry, Prometheus metrics endpoint, resource quotas, self-diagnosed

isn't handed 60+ overlapping tools by default.

• Opt-in tool surface — tools are grouped into toolsets you enable explicitly, so a client

caller supplies their own Qdrant, isolated by construction, protected by an SSRF guard.

• Read-only guard — one flag removes every mutating tool from the registry entirely.
• Bring-your-own-Qdrant mode — run a public endpoint with no database of your own; every

Qdrant's own error message on failure, never a generic exception.

• Resilient by default — every Qdrant call goes through retry-with-backoff and returns

Requirements

Shortened. The full README is on GitHub.