mcp-server-qdrant

To enable semantic search over your codebase using Claude Code, add the mcp-server-qdrant using the claude mcp add command. You must specify the Qdrant connection details, the collection name, and the embedding model to be used.

Once added, Claude Code can use the qdrant-store tool to save snippets and the qdrant-find tool to search for them using natural language queries.

# 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

# Verify the server was added
claude mcp list

To manually configure the Qdrant MCP server in VS Code, add a configuration block to your User Settings (JSON) or a workspace-specific .vscode/mcp.json file. You can choose between using uvx or docker as the execution command.

Both methods require defining inputs for qdrantUrl, qdrantApiKey, and collectionName to allow for secure and flexible configuration.

{
  "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}"
        }
      }
    }
  }
}

You can use the Qdrant MCP server as a code search tool in Cursor or Windsurf by running it with SSE (Server-Sent Events) transport and providing custom tool descriptions via environment variables. This allows the AI to store and retrieve code snippets using semantic search.

To set this up:

1. Run the server using uvx with the --transport sse flag.
2. Set QDRANT_URL, COLLECTION_NAME, TOOL_STORE_DESCRIPTION, and TOOL_FIND_DESCRIPTION environment variables.
3. In Cursor/Windsurf settings, point to the running server using the SSE transport protocol (e.g., http://localhost:8000/sse for local runs).

Note: If the tools aren't being used, consider creating Cursor rules to explicitly instruct the agent to use the MCP tools when generating code.

QDRANT_URL="http://localhost:6333" \
COLLECTION_NAME="code-snippets" \
TOOL_STORE_DESCRIPTION="Store reusable code snippets for later retrieval. \\nThe 'information' parameter should contain a natural language description of what the code does, \\nwhile the actual code should be included in the 'metadata' parameter as a 'code' property. \\nThe value of 'metadata' is a Python dictionary with strings as keys. \\nUse this whenever you generate some code snippet." \
TOOL_FIND_DESCRIPTION="Search for relevant code snippets based on natural language descriptions. \\nThe 'query' parameter should describe what you're looking for, \\nand the tool will return the most relevant code snippets. \\nUse this when you need to find existing code snippets for reuse or reference." \
uvx mcp-server-qdrant --transport sse # Enable SSE transport

If you prefer running the MCP server in an isolated container, use the following configuration in your VS Code User Settings (JSON) or .vscode/mcp.json. This setup maps port 8000 and passes the necessary Qdrant environment variables through to the container.

{
  "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}"
        }
      }
    }
  }
}

To use this server with Claude Desktop, add a configuration entry to the mcpServers section of your claude_desktop_config.json file.

Configuration for Remote Qdrant (Cloud/Server):

{
  "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"
    }
  }
}

Configuration for Local Qdrant:

{
  "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"
    }
  }
}

Note: The server will automatically create the specified collection if it does not exist.

The server is configured using environment variables.

Important Constraints:

• You cannot provide both QDRANT_URL and QDRANT_LOCAL_PATH at the same time.
• If COLLECTION_NAME is provided, the collection_name argument in tools becomes optional.

Qdrant Configuration Variables:

FastMCP Server Variables: