mcp-server-qdrant
MCP server for Qdrant vector database with local BERT embeddings. Enables semantic search and vector storage operations through natural language.
README
mcp-server-qdrant
Rust MCP server for Qdrant with local BERT embeddings. Single binary, no Python.
Why not the official Python one?
ONNX Python wheels are painful to package in Nix (especially aarch64-linux). This is a Rust rewrite with Nix-native packaging and a pure-Rust default backend (Candle) that has zero native dependencies.
Usage
Claude Desktop / Claude Code
With uvx (recommended):
{
"mcpServers": {
"qdrant": {
"command": "uvx",
"args": ["mcp-server-qdrant-rs"],
"env": {
"QDRANT_URL": "http://localhost:6334",
"COLLECTION_NAME": "my-collection"
}
}
}
}
With rvx:
{
"mcpServers": {
"qdrant": {
"command": "rvx",
"args": ["mcp-server-qdrant"],
"env": {
"QDRANT_URL": "http://localhost:6334",
"COLLECTION_NAME": "my-collection"
}
}
}
}
<details> <summary>Other installation methods</summary>
With Nix:
nix run github:vaporif/mcp-server-qdrant
# ONNX backend
nix run github:vaporif/mcp-server-qdrant#onnx
As a flake input:
{
inputs.mcp-server-qdrant.url = "github:vaporif/mcp-server-qdrant";
nixpkgs.overlays = [ mcp-server-qdrant.overlays.default ];
}
With cargo:
cargo install mcp-server-qdrant
From releases:
Download a prebuilt binary from GitHub Releases.
With Docker:
docker build -t mcp-server-qdrant .
docker run -p 8000:8000 -e QDRANT_URL=http://host.docker.internal:6334 -e COLLECTION_NAME=my-collection mcp-server-qdrant
</details>
HTTP Transport
mcp-server-qdrant --transport streamable-http --port 8000
Debugging
RUST_LOG=debug mcp-server-qdrant
Environment Variables
| Variable | Default | Description |
|---|---|---|
QDRANT_URL |
— | Qdrant server URL |
QDRANT_API_KEY |
— | Qdrant API key |
QDRANT_LOCAL_PATH |
— | Local storage path (instead of URL) |
COLLECTION_NAME |
— | Default collection name |
QDRANT_SEARCH_LIMIT |
10 | Max search results |
QDRANT_READ_ONLY |
false | Read-only mode |
EMBEDDING_MODEL |
sentence-transformers/all-MiniLM-L6-v2 | Model name |
MCP_TRANSPORT |
stdio | stdio, sse, streamable-http |
HOST |
127.0.0.1 | Bind host for SSE/HTTP |
PORT |
8000 | Bind port for SSE/HTTP |
Embedding Backends
| Feature | Description |
|---|---|
candle (default) |
Pure Rust. No native deps. |
onnx |
ONNX Runtime. Provide ORT_DYLIB_PATH. |
onnx-fetch |
ONNX with auto-download. |
Development
nix develop # dev shell
just check # clippy + test + fmt + taplo + typos
just test # run tests
just lint # clippy + fmt
just deny # dependency audit
just e2e # e2e tests (needs Qdrant)
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.