Qdrant

by qdrant

Recommended
448 stars
1 downloads
Not rated
GitHub

About

Implement semantic memory layer on top of the Qdrant vector search engine

Details

Author
qdrant
Repository
qdrant/mcp-server-qdrant
GitHub stars
448
Downloads
1
License
Apache License 2.0
Categories
Developer Tools, Database, Other, Knowledge Base, Search, AI

Jump to

- Semantic memory layer on top of Qdrant vector search.
- Store and retrieve information with optional metadata.
- Automatic collection creation if it does not exist.
- Configurable embedding model (FastEmbed models only).
- Works with any MCP-compatible client (Claude Desktop, Cursor, VS Code, etc.).
- Customizable tool descriptions via environment variables.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Qdrant
    Command (node, npx, python, etc.) uvx
    Arguments
    • Argument 1 mcp-server-qdrant
    Environment
    • QDRANT_URL https://xyz-example.eu-central.aws.cloud.qdrant.io:6333
    • QDRANT_API_KEY your_api_key
    • COLLECTION_NAME your-collection-name
    • EMBEDDING_MODEL sentence-transformers/all-MiniLM-L6-v2

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Configuration is done via environment variables. The only command-line argument is --transport, used to select the transport protocol.

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

| Name | Description | Default Value |
|--------------------------|---------------------------------------------------------------------|-------------------------------------------------------------------|
| QDRANT_URL | URL of the Qdrant server | None |
| QDRANT_API_KEY | API key for the Qdrant server | None |
| COLLECTION_NAME | Name of the default collection to use. | None |
| QDRANT_LOCAL_PATH | Path to the local Qdrant database (alternative to QDRANT_URL) | None |
| EMBEDDING_PROVIDER | Embedding provider to use (currently only "fastembed" is supported) | fastembed |
| EMBEDDING_MODEL | Name of the embedding model to use | sentence-transformers/all-MiniLM-L6-v2 |
| TOOL_STORE_DESCRIPTION | Custom description for the store tool | See default in settings.py |
| TOOL_FIND_DESCRIPTION | Custom description for the find tool | See default in settings.py |
| QDRANT_SEARCH_LIMIT | Maximum number of results to return from search | 10 |
| QDRANT_READ_ONLY | Enable read-only mode (disables qdrant-store tool) | false |

Since mcp-server-qdrant is based on FastMCP, it also supports all the FastMCP environment variables. The most
important ones are listed below:

| Environment Variable | Description | Default Value |
|--------------------------------------------|-----------------------------------------------------------------|---------------|
| FASTMCP_LOG_LEVEL | Set logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL) | INFO |
| FASTMCP_SERVER_DEBUG | Enable debug mode | false |
| FASTMCP_SERVER_HOST | Host address to bind the server to | 127.0.0.1 |
| FASTMCP_SERVER_PORT | Port to run the server on | 8000 |
| FASTMCP_SERVER_ON_DUPLICATE_RESOURCES | Behavior for duplicate resources (warn, error, replace, ignore) | warn |
| FASTMCP_SERVER_ON_DUPLICATE_TOOLS | Behavior for duplicate tools (warn, error, replace, ignore) | warn |
| FASTMCP_SERVER_ON_DUPLICATE_PROMPTS | Behavior for duplicate prompts (warn, error, replace, ignore) | warn |
| FASTMCP_SERVER_DEPENDENCIES | List of dependencies to install in the server environment | [] |

> [!NOTE]
> Server-specific settings use the FASTMCP_SERVER_ prefix. This may change in future versions.

To install Qdrant MCP Server for Claude Desktop automatically via Smithery:

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

To use this server with the Claude Desktop app, add the following configuration to the "mcpServers" section of your
claude_desktop_config.json:

{
  "qdrant": {
    "command": "uvx",
    "args": ["mcp-server-qdrant"],
    "env": {
      "QDRANT_URL": "https://xyz-example.eu-central.aws.cloud.qdrant.io:6333",
      "QDRANT_API_KEY": "your_api_key",
      "COLLECTION_NAME": "your-collection-name",
      "EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2"
    }
  }
}

For local Qdrant mode:

{
  "qdrant": {
    "command": "uvx",
    "args": ["mcp-server-qdrant"],
    "env": {
      "QDRANT_LOCAL_PATH": "/path/to/qdrant/database",
      "COLLECTION_NAME": "your-collection-name",
      "EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2"
    }
  }
}

This MCP server will automatically create a collection with the specified name if it doesn't exist.

By default, the server will use the sentence-transformers/all-MiniLM-L6-v2 embedding model to encode memories.
For the time being, only FastEmbed models are supported.

qdrant-store

Store some information in the Qdrant database. Parameters: information (string), metadata (JSON, optional), collection_name (string, required if no default collection name)

qdrant-find

Retrieve relevant information from the Qdrant database. Parameters: query (string), collection_name (string, required if no default collection name)

1. qdrant-store
- Store some information in the Qdrant database
- Input:
- information (string): Information to store
- metadata (JSON): Optional metadata to store
- collection_name (string): Name of the collection to store the information in. This field is required if there are no default collection name.
If there is a default collection name, this field is not enabled.
- Returns: Confirmation message
2. qdrant-find
- Retrieve relevant information from the Qdrant database
- Input:
- query (string): Query to use for searching
- collection_name (string): Name of the collection to store the information in. This field is required if there are no default collection name.
If there is a default collection name, this field is not enabled.
- Returns: Information stored in the Qdrant database as separate messages

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "qdrant": {
            "env": {
                "QDRANT_URL": "https://xyz-example.eu-central.aws.cloud.qdrant.io:6333",
                "QDRANT_API_KEY": "your_api_key",
                "COLLECTION_NAME": "your-collection-name",
                "EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2"
            },
            "args": [
                "mcp-server-qdrant"
            ],
            "command": "uvx"
        }
    }
}

Linux

{
    "env": {
        "QDRANT_URL": "https://xyz-example.eu-central.aws.cloud.qdrant.io:6333",
        "QDRANT_API_KEY": "your_api_key",
        "COLLECTION_NAME": "your-collection-name",
        "EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2"
    },
    "args": [
        "mcp-server-qdrant"
    ],
    "command": "uvx"
}

Macos

{
    "env": {
        "QDRANT_URL": "https://xyz-example.eu-central.aws.cloud.qdrant.io:6333",
        "QDRANT_API_KEY": "your_api_key",
        "COLLECTION_NAME": "your-collection-name",
        "EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2"
    },
    "args": [
        "mcp-server-qdrant"
    ],
    "command": "uvx"
}

Windows

{
    "env": {
        "QDRANT_URL": "https://xyz-example.eu-central.aws.cloud.qdrant.io:6333",
        "QDRANT_API_KEY": "your_api_key",
        "COLLECTION_NAME": "your-collection-name",
        "EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2"
    },
    "args": [
        "mcp-server-qdrant"
    ],
    "command": "uvx"
}

Use Qdrant as a semantic memory layer for your AI assistant, letting it store and retrieve information by meaning rather than exact keywords.

- Store semantic memories— Ask your assistant to save information with optional metadata to Qdrant viaqdrant-storefor later retrieval.
- Retrieve relevant memories— Useqdrant-findto search stored information with a natural language query and get matching results.
- Build a code snippet library— Store code snippets with descriptions and retrieve them semantically, as shown in the Cursor and Claude Code setups.
- Target specific collections— Store or search in a named collection viacollection_name, or rely on the default set byCOLLECTION_NAME.

TheModel Context Protocol (MCP)is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you're building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need.

This repository is an example of how to create a MCP server forQdrant, a vector search engine.

An official Model Context Protocol server for keeping and retrieving memories in the Qdrant vector search engine. It acts as a semantic memory layer on top of the Qdrant database.
- qdrant-store

- Store some information in the Qdrant database
- Input:

- information(string): Information to store
- metadata(JSON): Optional metadata to store
- collection_name(string): Name of the collection to store the information in. This field is required if there are no default collection name. If there is a default collection name, this field is not enabled.

- Retrieve relevant information from the Qdrant database
- Input:

- query(string): Query to use for searching
- collection_name(string): Name of the collection to store the information in. This field is required if there are no default collection name. If there is a default collection name, this field is not enabled.

Configuration is done via environment variables. The only command-line argument is--transport, used to select thetransport protocol.

[!NOTE] You cannot provide bothQDRANT_URLandQDRANT_LOCAL_PATHat the same time.

Sincemcp-server-qdrantis based on FastMCP, it also supports all the FastMCP environment variables. The most important ones are listed below:

[!NOTE] Server-specific settings use theFASTMCP_SERVER_prefix. This may change in future versions.

When usinguvxno specific installation is needed to directly runmcp-server-qdrant.

QDRANT_URL="http://localhost:6333" \ COLLECTION_NAME="my-collection" \ EMBEDDING_MODEL="sentence-transformers/all-MiniLM-L6-v2" \ uvx mcp-server-qdrant

The server supports different transport protocols that can be specified using the--transportflag:

QDRANT_URL="http://localhost:6333" \ COLLECTION_NAME="my-collection" \ uvx mcp-server-qdrant --transport sse

- stdio(default): Standard input/output transport, might only be used by local MCP clients
- sse: Server-Sent Events transport, perfect for remote clients
- streamable-http: Streamable HTTP transport, perfect for remote clients, more recent than SSE

The default transport isstdioif not specified.

When SSE transport is used, the server will listen on the specified port and wait for incoming connections. The default port is 8000, however it can be changed using theFASTMCP_SERVER_PORTenvironment variable.

QDRANT_URL="http://localhost:6333" \ COLLECTION_NAME="my-collection" \ FASTMCP_SERVER_PORT=1234 \ uvx mcp-server-qdrant --transport sse

A Dockerfile is available for building and running the MCP server:

# Build the container docker build -t mcp-server-qdrant . # Run the container docker run -p 8000:8000 \ -e FASTMCP_SERVER_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" \ mcp-server-qdrant

[!TIP] Please note that we setFASTMCP_SERVER_HOST="0.0.0.0"to make the server listen on all network interfaces. This is necessary when running the server in a Docker container.

To install Qdrant MCP Server for Claude Desktop automatically viaSmithery:

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

To use this server with the Claude Desktop app, add the following configuration to the "mcpServers" section of yourclaude_desktop_config.json:

{ "qdrant": { "command": "uvx", "args": ["mcp-server-qdrant"], "env": { "QDRANT_URL": "https://xyz-example.eu-central.aws.cloud.qdrant.io:6333", "QDRANT_API_KEY": "your_api_key", "COLLECTION_NAME": "your-collection-name", "EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2" } } }

{ "qdrant": { "command": "uvx", "args": ["mcp-server-qdrant"], "env": { "QDRANT_LOCAL_PATH": "/path/to/qdrant/database", "COLLECTION_NAME": "your-collection-name", "EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2" } } }

This MCP server will automatically create a collection with the specified name if it doesn't exist.

By default, the server will use thesentence-transformers/all-MiniLM-L6-v2embedding model to encode memories. For the time being, onlyFastEmbedmodels are supported.

This MCP server can be used with any MCP-compatible client. For example, you can use it withCursorandVS Code, which provide built-in support for the Model Context Protocol.

You can configure this MCP server to work as a code search tool for Cursor or Windsurf by customizing the tool descriptions:

QDRANT_URL="http://localhost:6333" \ COLLECTION_NAME="code-snippets" \ 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. \ The value of 'metadata' is a Python dictionary with strings as keys. \ Use this whenever you generate some code snippet." \ TOOL_FIND_DESCRIPTION="Search for relevant code snippets based on natural language descriptions. \ The 'query' parameter should describe what you're looking for, \ and the tool will return the most relevant code snippets. \ Use this when you need to find existing code snippets for reuse or reference." \ uvx mcp-server-qdrant --transport sse # Enable SSE transport

In Cursor/Windsurf, you can then configure the MCP server in your settings by pointing to this running server using SSE transport protocol. The description on how to add an MCP server to Cursor can be found in theCursor documentation. If you are running Cursor/Windsurf locally, you can use the following URL:

[!TIP] We suggest SSE transport as a preferred way to connect Cursor/Windsurf to the MCP server, as it can support remote connections. That makes it easy to share the server with your team or use it in a cloud environment.

This configuration transforms the Qdrant MCP server into a specialized code search tool that can:
- Store code snippets, documentation, and implementation details
- Retrieve relevant code examples based on semantic search
- Help developers find specific implementations or usage patterns

You can populate the database by storing natural language descriptions of code snippets (in theinformationparameter) along with the actual code (in themetadata.codeproperty), and then search for them using natural language queries that describe what you're looking for.

[!NOTE] The tool descriptions provided above are examples and may need to be customized for your specific use case. Consider adjusting the descriptions to better match your team's workflow and the specific types of code snippets you want to store and retrieve.

If you have successfully installed themcp-server-qdrant, but still can't get it to work with Cursor, please consider creating theCursor rulesso the MCP tools are always used when the agent produces a new code snippet.You can restrict the rules to only work for certain file types, to avoid using the MCP server for the documentation or other types of content.

You can enhance Claude Code's capabilities by connecting it to this MCP server, enabling semantic search over your existing codebase.

# Add mcp-server-qdrant configured for code search claude mcp add code-search \ -e QDRANT_URL="http://localhost:6333" \ -e COLLECTION_NAME="code-repository" \ -e EMBEDDING_MODEL="sentence-transformers/all-MiniLM-L6-v2" \ -e TOOL_STORE_DESCRIPTION="Store code snippets with descriptions. 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." \ -e TOOL_FIND_DESCRIPTION="Search for relevant code snippets using natural language. The 'query' parameter should describe the functionality you're looking for." \ -- uvx mcp-server-qdrant

Using Semantic Code Search in Claude Code

Tool descriptions, specified inTOOL_STORE_DESCRIPTIONandTOOL_FIND_DESCRIPTION, guide Claude Code on how to use the MCP server. The ones provided above are examples and may need to be customized for your specific use case. However, Claude Code should be already able to:
- Use theqdrant-storetool to store code snippets with descriptions.
- Use theqdrant-findtool to search for relevant code snippets using natural language.

The MCP server can be run in development mode using themcp devcommand. This will start the server and open the MCP inspector in your browser.

COLLECTION_NAME=mcp-dev fastmcp dev src/mcp_server_qdrant/server.py

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

Add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressingCtrl + Shift + Pand typingPreferences: Open User Settings (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}" } } } } }

Or if you prefer using Docker, add this configuration instead:

{ "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": "docker", "args": [ "run", "-p", "8000:8000", "-i", "--rm", "-e", "QDRANT_URL", "-e", "QDRANT_API_KEY", "-e", "COLLECTION_NAME", "mcp-server-qdrant" ], "env": { "QDRANT_URL": "${input:qdrantUrl}", "QDRANT_API_KEY": "${input:qdrantApiKey}", "COLLECTION_NAME": "${input:collectionName}" } } } } }

Alternatively, you can create a.vscode/mcp.jsonfile in your workspace with the following content:

{ "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}" } } } }

For workspace configuration with Docker, use this in.vscode/mcp.json:

{ "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": "docker", "args": [ "run", "-p", "8000:8000", "-i", "--rm", "-e", "QDRANT_URL", "-e", "QDRANT_API_KEY", "-e", "COLLECTION_NAME", "mcp-server-qdrant" ], "env": { "QDRANT_URL": "${input:qdrantUrl}", "QDRANT_API_KEY": "${input:qdrantApiKey}", "COLLECTION_NAME": "${input:collectionName}" } } } }

If you have suggestions for how mcp-server-qdrant could be improved, or want to report a bug, open an issue! We'd love all and any contributions.

TheMCP inspectoris a developer tool for testing and debugging MCP servers. It runs both a client UI (default port 5173) and an MCP proxy server (default port 3000). Open the client UI in your browser to use the inspector.

QDRANT_URL=":memory:" COLLECTION_NAME="test" \ fastmcp dev src/mcp_server_qdrant/server.py

Once started, open your browser tohttp://localhost:5173to access the inspector interface.

This MCP server is licensed under the Apache License 2.0. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the Apache License 2.0. For more details, please see the LICENSE file in the project repository.

Semantic search using the Qdrant vector database.

Search, Query and interact with data in your Milvus Vector Database.

Implement semantic memory layer on top of the Qdrant vector search engine

An MCP server for vector storage and retrieval using ChromaDB.

Interact with on-disk documents using agentic RAG and hybrid search via LanceDB.

Connect AI tools with Pinecone projects to search, configure indexes, generate code, and manage data.

A containerized MCP server for LanceDB vector search, featuring hybrid processing with Gemini and Ollama.

Semantic code search using the Qdrant vector database and OpenAI embeddings.

Embeddings, vector search, document storage, and full-text search with the open-source AI application database

Semantic search over 4.6M+ text chunks from 20,000+ classical philosophy and humanities works — Plato, Aristotle, Kant, Nietzsche, and thousands more. Multilingual (Greek, Latin, German, French, English). No install needed.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

Install

Add to Claude Desktop or Cursor

{
    "mcpServers": {
        "qdrant": {
            "env": {
                "QDRANT_URL": "https://xyz-example.eu-central.aws.cloud.qdrant.io:6333",
                "QDRANT_API_KEY": "your_api_key",
                "COLLECTION_NAME": "your-collection-name",
                "EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2"
            },
            "args": [
                "mcp-server-qdrant"
            ],
            "command": "uvx"
        }
    }
}

More like this

Similar MCP servers you might find useful

Browse category

Sequential Thinking

Sequential Thinking is an MCP server that provides a tool for dynamic and reflective problem-solving through a structured, step-by-step thinking process. It is…

88.2k
Other

Filesystem

Filesystem is a Node.js server that implements the Model Context Protocol (MCP) for filesystem operations. It enables AI assistants to read, write, and manage…

88.1k
Other