# mcp-server-qdrant: Hybrid Search Fork

> Forked from [qdrant/mcp-server-qdrant](https://github.com/qdrant/mcp-server-qdrant) — the official MCP server for Qdrant.

An [MCP](https://modelcontextprotocol.io/introduction) server for [Qdrant](https://qdrant.tech/) vector search engine that acts as a **semantic memory layer** for LLM applications.

This fork adds two features on top of the upstream:

1. **Hybrid Search** — combines dense (semantic) and sparse (BM25 keyword) vectors using Reciprocal Rank Fusion for significantly better recall
2. **Project Tagging** — automatic `project` metadata on every stored memory, with a payload index for efficient filtering

Everything else remains fully compatible with the upstream.

---

## What's Different in This Fork

### Hybrid Search (Dense + BM25 Sparse with RRF)

The upstream server uses **dense vectors only** (semantic similarity). This works well for paraphrased queries but can miss results when the user searches for exact terms, names, or identifiers.

This fork adds **BM25 sparse vectors** alongside the dense ones. At query time, both vector spaces are searched independently and results are fused using **Reciprocal Rank Fusion (RRF)** — a proven technique that combines rankings without requiring score calibration.

**How it works:**

```
Store: document → [dense embedding] + [BM25 sparse embedding] → Qdrant
Search: query → prefetch(dense, top-k) + prefetch(BM25, top-k) → RRF fusion → final results
```

- Dense vectors capture **semantic meaning** (synonyms, paraphrases, context)
- BM25 sparse vectors excel at **exact keyword matching** (names, IDs, error codes)
- RRF fusion gives you the best of both worlds

**Enable it** with a single environment variable:

```bash
HYBRID_SEARCH=true
```

> [!NOTE]
> Hybrid search uses the `Qdrant/bm25` model from [FastEmbed](https://qdrant.github.io/fastembed/) for sparse embeddings. The model is downloaded automatically on first use (~50 MB). The IDF modifier is applied to upweight rare terms in the corpus.

> [!IMPORTANT]
> Enabling hybrid search on an existing collection requires re-creating it, as the sparse vector configuration must be set at collection creation time. Back up your data before switching.

### Project Tagging

The `qdrant-store` tool now accepts a `project` parameter (default: `"global"`). This value is automatically injected into the metadata of every stored record and indexed as a keyword field for efficient filtering.

This is useful when multiple projects share the same Qdrant collection — you can tag memories with the project name and filter by it later.

```
qdrant-store(information="...", project="my-project")
→ metadata: {"project": "my-project", ...}
```

A payload index on `metadata.project` is created automatically when the collection is first set up.

---

## Tools

### `qdrant-store`

Store information in the Qdrant database.

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `information` | string | yes | Text to store |
| `project` | string | no | Project name to tag this memory with. Default: `"global"`. Use the project name (e.g. `"my-app"`) for project-specific knowledge, or `"global"` for cross-project knowledge. |
| `metadata` | JSON | no | Extra metadata stored alongside the information |
| `collection_name` | string | depends | Collection name. Required if no default is configured. |

### `qdrant-find`

Retrieve relevant information from the Qdrant database.

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `query` | string | yes | What to search for |
| `collection_name` | string | depends | Collection name. Required if no default is configured. |

## Environment Variables

| Name | Description | Default |
|------|-------------|---------|
| `QDRANT_URL` | URL of the Qdrant server | None |
| `QDRANT_API_KEY` | API key for the Qdrant server | None |
| `QDRANT_LOCAL_PATH` | Path to local Qdrant database (alternative to `QDRANT_URL`) | None |
| `COLLECTION_NAME` | Default collection name | None |
| `EMBEDDING_PROVIDER` | Embedding provider (currently only `fastembed`) | `fastembed` |
| `EMBEDDING_MODEL` | Embedding model name | `sentence-transformers/all-MiniLM-L6-v2` |
| **`HYBRID_SEARCH`** | **Enable hybrid search (dense + BM25 sparse with RRF)** | **`false`** |
| `QDRANT_SEARCH_LIMIT` | Maximum number of results per search | `10` |
| `QDRANT_READ_ONLY` | Disable write operations (store tool) | `false` |
| `QDRANT_ALLOW_ARBITRARY_FILTER` | Allow arbitrary filter objects in find queries | `false` |
| `TOOL_STORE_DESCRIPTION` | Custom description for the store tool | See [`settings.py`](src/mcp_server_qdrant/settings.py) |
| `TOOL_FIND_DESCRIPTION` | Custom description for the find tool | See [`settings.py`](src/mcp_server_qdrant/settings.py) |

> [!IMPORTANT]
> You cannot provide both `QDRANT_URL` and `QDRANT_LOCAL_PATH` at the same time.

### FastMCP Environment Variables

Since `mcp-server-qdrant` is based on FastMCP, it also supports all FastMCP environment variables:

| Name | Description | Default |
|------|-------------|---------|
| `FASTMCP_DEBUG` | Enable debug mode | `false` |
| `FASTMCP_LOG_LEVEL` | Log level (DEBUG, INFO, WARNING, ERROR, CRITICAL) | `INFO` |
| `FASTMCP_HOST` | Host address to bind to | `127.0.0.1` |
| `FASTMCP_PORT` | Port to run the server on | `8000` |

## Installation

### Using uvx

No installation needed with [`uvx`](https://docs.astral.sh/uv/guides/tools/#running-tools):

```shell
QDRANT_URL="http://localhost:6333" \
COLLECTION_NAME="my-collection" \
HYBRID_SEARCH=true \
uvx mcp-server-qdrant
```

#### Transport Protocols

```shell
# SSE transport (for remote clients)
QDRANT_URL="http://localhost:6333" \
COLLECTION_NAME="my-collection" \
HYBRID_SEARCH=true \
uvx mcp-server-qdrant --transport sse
```

Supported transports:
- `stdio` (default) — for local MCP clients
- `sse` — Server-Sent Events, for remote clients
- `streamable-http` — streamable HTTP, newer alternative to SSE

### Using Docker

```bash
docker build -t mcp-server-qdrant .

docker run -p 8000:8000 \
  -e FASTMCP_HOST="0.0.0.0" \
  -e QDRANT_URL="http://your-qdrant-server:6333" \
  -e QDRANT_API_KEY="your-api-key" \
  -e COLLECTION_NAME="your-collection" \
  -e HYBRID_SEARCH=true \
  mcp-server-qdrant
```

### Installing via Smithery

```bash
npx @smithery/cli install mcp-server-qdrant --client claude
```

## Usage with MCP Clients

### Claude Desktop

Add to `claude_desktop_config.json`:

```json
{
  "qdrant": {
    "command": "uvx",
    "args": ["mcp-server-qdrant"],
    "env": {
      "QDRANT_URL": "https://your-qdrant-instance:6333",
      "QDRANT_API_KEY": "your_api_key",
      "COLLECTION_NAME": "your-collection",
      "EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2",
      "HYBRID_SEARCH": "true"
    }
  }
}
```

### Claude Code

```shell
claude mcp add qdrant-memory \
  -e QDRANT_URL="http://localhost:6333" \
  -e COLLECTION_NAME="my-memory" \
  -e HYBRID_SEARCH="true" \
  -- uvx mcp-server-qdrant
```

Verify:

```shell
claude mcp list
```

### Cursor / Windsurf

Run the server with SSE transport and custom tool descriptions for code search:

```bash
QDRANT_URL="http://localhost:6333" \
COLLECTION_NAME="code-snippets" \
HYBRID_SEARCH=true \
TOOL_STORE_DESCRIPTION="Store reusable code snippets for later retrieval. \
The 'information' parameter should contain a natural language description of what the code does, \
while the actual code should be included in the 'metadata' parameter as a 'code' property." \
TOOL_FIND_DESCRIPTION="Search for relevant code snippets based on natural language descriptions." \
uvx mcp-server-qdrant --transport sse
```

Then point Cursor/Windsurf to `http://localhost:8000/sse`.

### VS Code

For one-click installation, click one of the install buttons below:

[![Install with UVX in VS Code](https://img.shields.io/badge/VS_Code-UVX-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=qdrant&config=%7B%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22mcp-server-qdrant%22%5D%2C%22env%22%3A%7B%22QDRANT_URL%22%3A%22%24%7Binput%3AqdrantUrl%7D%22%2C%22QDRANT_API_KEY%22%3A%22%24%7Binput%3AqdrantApiKey%7D%22%2C%22COLLECTION_NAME%22%3A%22%24%7Binput%3AcollectionName%7D%22%7D%7D&inputs=%5B%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22qdrantUrl%22%2C%22description%22%3A%22Qdrant+URL%22%7D%2C%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22qdrantApiKey%22%2C%22description%22%3A%22Qdrant+API+Key%22%2C%22password%22%3Atrue%7D%2C%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22collectionName%22%2C%22description%22%3A%22Collection+Name%22%7D%5D) [![Install with UVX in VS Code Insiders](https://img.shields.io/badge/VS_Code_Insiders-UVX-24bfa5?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=qdrant&config=%7B%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22mcp-server-qdrant%22%5D%2C%22env%22%3A%7B%22QDRANT_URL%22%3A%22%24%7Binput%3AqdrantUrl%7D%22%2C%22QDRANT_API_KEY%22%3A%22%24%7Binput%3AqdrantApiKey%7D%22%2C%22COLLECTION_NAME%22%3A%22%24%7Binput%3AcollectionName%7D%22%7D%7D&inputs=%5B%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22qdrantUrl%22%2C%22description%22%3A%22Qdrant+URL%22%7D%2C%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22qdrantApiKey%22%2C%22description%22%3A%22Qdrant+API+Key%22%2C%22password%22%3Atrue%7D%2C%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22collectionName%22%2C%22description%22%3A%22Collection+Name%22%7D%5D&quality=insiders)

Or add manually to VS Code settings (`Ctrl+Shift+P` → `Preferences: Open User Settings (JSON)`):

```json
{
  "mcp": {
    "inputs": [
      {"type": "promptString", "id": "qdrantUrl", "description": "Qdrant URL"},
      {"type": "promptString", "id": "qdrantApiKey", "description": "Qdrant API Key", "password": true},
      {"type": "promptString", "id": "collectionName", "description": "Collection Name"}
    ],
    "servers": {
      "qdrant": {
        "command": "uvx",
        "args": ["mcp-server-qdrant"],
        "env": {
          "QDRANT_URL": "${input:qdrantUrl}",
          "QDRANT_API_KEY": "${input:qdrantApiKey}",
          "COLLECTION_NAME": "${input:collectionName}",
          "HYBRID_SEARCH": "true"
        }
      }
    }
  }
}
```

## Development

Run in development mode with the MCP inspector:

```shell
COLLECTION_NAME=mcp-dev HYBRID_SEARCH=true \
fastmcp dev src/mcp_server_qdrant/server.py
```

Open http://localhost:5173 to access the inspector.

## How Hybrid Search Works Under the Hood

When `HYBRID_SEARCH=true`:

**Storing:**
1. The document is embedded with the dense model (e.g. `all-MiniLM-L6-v2`) → semantic vector
2. The document is also embedded with `Qdrant/bm25` → sparse vector (term frequencies with IDF)
3. Both vectors are stored in the same Qdrant point

**Searching:**
1. The query is embedded with both models
2. Two independent prefetch queries run in parallel:
   - Dense vector search (cosine similarity)
   - BM25 sparse vector search (dot product with IDF weighting)
3. Results are fused using **Reciprocal Rank Fusion**: `score = 1/(k + rank_dense) + 1/(k + rank_sparse)`
4. Top-k fused results are returned

This approach is battle-tested in information retrieval and consistently outperforms either method alone, especially for queries that mix natural language with specific terms.

## Acknowledgments

This is a fork of [qdrant/mcp-server-qdrant](https://github.com/qdrant/mcp-server-qdrant). All credit for the original implementation goes to the Qdrant team.

## License

Apache License 2.0 — see [LICENSE](LICENSE) for details.