mcp-server-qdrant
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-server-qdrantsearch for documents similar to 'machine learning'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
Related MCP server: qdrant-mcp
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"
}
}
}
}With Nix:
nix run github:vaporif/mcp-server-qdrant
# ONNX backend
nix run github:vaporif/mcp-server-qdrant#onnxAs 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-qdrantFrom 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-qdrantHTTP Transport
mcp-server-qdrant --transport streamable-http --port 8000Debugging
RUST_LOG=debug mcp-server-qdrantEnvironment Variables
Variable | Default | Description |
| — | Qdrant server URL |
| — | Qdrant API key |
| — | Local storage path (instead of URL) |
| — | Default collection name |
| 10 | Max search results |
| false | Read-only mode |
| sentence-transformers/all-MiniLM-L6-v2 | Model name |
| stdio |
|
| 127.0.0.1 | Bind host for SSE/HTTP |
| 8000 | Bind port for SSE/HTTP |
Embedding Backends
Feature | Description |
| Pure Rust. No native deps. |
| ONNX Runtime. Provide |
| 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
This server cannot be deployed
Maintenance
Related MCP Connectors
Remote ChromaDB vector database MCP server with streamable HTTP transport
DocBase MCP server for AI agents
Personal knowledge base MCP server with semantic search, auto-categorization, metadata extraction
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Machine Control Protocol (MCP) server that enables storing and retrieving information from a Qdrant vector database with semantic search capabilities.Apache 2.0
- AlicenseNot gradedqualityDmaintenanceMCP server for document ingestion and semantic search on Qdrant. Enables ingesting local documents, generating embeddings with OpenAI, and performing vector search with metadata filters.Apache 2.0
- AlicenseNot gradedqualityDmaintenanceA knowledge base MCP server backed by Qdrant vector database with local embeddings for semantic search and document management.5 npm1ISC
- AlicenseNot gradedqualityCmaintenanceMCP server that searches documents in Qdrant using embeddings from LMStudio. Takes a text query, converts it to a vector via LMStudio's OpenAI-compatible API, and performs semantic search in Qdrant.15 npmISC