Log inSubmit server
Qdrant MCP logo

Qdrant MCP

Manage Qdrant collections, points, payloads, indexes, and advanced vector queries through MCP.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Qdrant MCP

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "qdrant-mcp": {
      "command": "uvx",
      "args": [
        "mcp-qdrant"
      ],
      "env": {
        "QDRANT_URL": "YOUR_VALUE_HERE",
        "QDRANT_MCP_TRANSPORT": "YOUR_VALUE_HERE",
        "QDRANT_MCP_HTTP_HOST": "YOUR_VALUE_HERE",
        "QDRANT_MCP_SHARED_SECRET": "YOUR_VALUE_HERE",
        "QDRANT_MCP_TOOLSETS": "YOUR_VALUE_HERE",
        "QDRANT_MCP_MAX_LIMIT": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

Qdrant MCP connects an MCP client to the Qdrant vector database API and exposes collection, point, payload, and search operations as tools. It uses the official Qdrant Python client, validates tool inputs, and passes vectors supplied by the calling application to Qdrant without generating embeddings or chunking documents. Reach for it when an agent needs to administer a Qdrant deployment, maintain vector data, or use query modes such as hybrid search, reranking, recommendation, discovery, and grouped results. It supports local stdio execution and remote streamable HTTP deployments.

Use cases

  • Create and maintain Qdrant collections
  • Insert and update application-generated vectors
  • Run hybrid or grouped similarity searches
  • Manage payload fields and filter indexes
  • Inspect and administer a Qdrant deployment

Key features

  • Collection and point lifecycle operations
  • Hybrid, reranking, MMR, recommendation, and discovery queries
  • Batch queries and grouped results
  • Payload editing, faceting, and indexing
  • Named vector management
  • Local stdio and streamable HTTP transports

Tools56

What Qdrant MCP lets your agent do. Expand a tool for its parameters.

Self-reported~1.8k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

9/9 checks healthy over the last 46d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 6d ago via OSV.dev · mcp-qdrant (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars2Stargazers on the source repository.
Last commit2d agoMost recent push to the default branch.
Tools exposed56Callable tools this server registers over MCP.

How Qdrant MCP works

What Qdrant MCP does

Qdrant MCP gives an MCP-compatible AI client direct access to selected Qdrant database operations. Its tools cover the collection lifecycle, point storage and retrieval, payload maintenance, payload indexes, named vector creation, health checks, and advanced search workflows.

The server expects the calling client to provide vectors when inserting or searching data. It does not create embeddings, split documents, or implement a retrieval-augmented generation pipeline. That makes it suitable for agents that already have an embedding workflow or need database administration rather than document ingestion.

How it works

Each MCP tool maps to a Qdrant operation and calls the official qdrant-client SDK after validating its arguments. Results and Qdrant errors are returned through MCP. The server can run locally over stdio or expose a streamable HTTP endpoint for a network-accessible client.

Collection tools create, inspect, update, list, and delete collections. Point tools upsert, fetch, delete, scroll, and count records. Payload tools can merge, replace, remove, or clear fields, count distinct values, and manage payload indexes. Search tools support vector queries, hybrid fusion, prefetch-based multi-stage searches, MMR, score formulas, payload ordering, random sampling, grouped queries, recommendations, discovery, and distance matrices.

Queries and recommendations also have batch variants, allowing multiple independent operations against one collection in a single round trip. Filters can be used with scrolling, counting, deletion, and payload operations where supported by the tool.

Setup and configuration

The package requires Python 3.12 or newer. Qdrant server 1.19.0 or newer is the tested target, although most operations can work with older Qdrant versions. Set QDRANT_URL to the Qdrant endpoint, then start the package with uvx mcp-qdrant or install it with pip install mcp-qdrant.

For a local stdio setup, point the server at Qdrant with a command such as:

bash
QDRANT_URL=http://localhost:6333 mcp-qdrant

Docker deployments use streamable HTTP. Set QDRANT_MCP_TRANSPORT=streamable-http, bind the HTTP service with QDRANT_MCP_HTTP_HOST=0.0.0.0 when it must be reachable outside the container, and provide QDRANT_MCP_SHARED_SECRET. The shared secret is required for streamable HTTP. Claude Desktop can also install the downloadable .mcpb bundle and configure the connection through its settings form.

Tools and capabilities

  • Check Qdrant health and list, inspect, create, update, or remove collections.
  • Add, retrieve, scroll, count, or delete points using IDs and payload filters.
  • Create collections with unnamed or named vectors, including dense, sparse, and multivector configurations where supported by the inputs.
  • Run vector, hybrid, grouped, recommendation, discovery, batch, and distance-matrix searches.
  • Edit payload fields, calculate facets, and create or remove payload indexes.
  • Add a named vector to an existing collection without modifying its stored points.

The server also supports configurable toolsets and a read-only mode that removes mutating tools from the exposed registry.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Qdrant MCP

Qdrant MCP is an MCP server that connects AI clients to the Qdrant vector database through the official Python client. Its main tools manage collections, points, payloads, indexes, and named vectors, and run vector, hybrid, grouped, recommendation, discovery, batch, and distance-matrix queries using vectors supplied by the client.

Install it with `pip install mcp-qdrant` or run it without a local installation using `uvx mcp-qdrant`. The project also publishes a Docker image for streamable HTTP deployments and a downloadable `.mcpb` bundle for Claude Desktop.

Set `QDRANT_URL` to the local Qdrant endpoint and start the server, for example `QDRANT_URL=http://localhost:6333 mcp-qdrant`. Configure the command in the MCP client using the stdio transport.

Yes. Claude Desktop can launch it through a stdio configuration using `uvx mcp-qdrant`, or install the `.mcpb` bundle and configure the Qdrant connection through the desktop settings form.

No. Qdrant MCP does not generate embeddings, parse documents, or choose text chunks. The calling application must supply vectors for storage and search.

Related MCP servers

All in Databases All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewQdrant MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/qdrant-mcp?style=directory)](https://allmcps.com/mcp/qdrant-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/qdrant-mcp"><img src="https://allmcps.com/api/badge/qdrant-mcp?style=directory" alt="Qdrant MCP on AllMCPs" /></a>