How to Use the Qdrant MCP in Google ADK

Q: Can I monitor Qdrant collection sizes using Google ADK?

Yes, you can use the count tool to get the exact number of active points in a Qdrant collection. This is useful for verifying that data pipelines from BigQuery have finished indexing. The Google ADK handles the response format so your Gemini agent can use the metric in its logic.

Q: How do I paginate through Qdrant payloads with Google ADK?

You use the scroll tool to paginate through Qdrant points and retrieve their payload data. This is ideal when Gemini needs to process a large volume of metadata that exceeds standard search limit sizes. The Google ADK returns the points in manageable chunks to prevent memory issues.

Q: What happens if my Google ADK agent tries to delete Qdrant points?

The agent will execute the delete tool using the point IDs you provide to remove them from the Qdrant collection via the MCP connection. Since this action is irreversible, you should restrict tool access in your Google ADK configuration if you want to prevent accidental data loss.

Connect Gemini models to your Qdrant vector database using Google ADK to run similarity searches over million-token contexts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Qdrant MCP to Google ADK

Create your Vinkius account to connect Qdrant to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Qdrant with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-context vector retrieval via Google ADK

The `search` tool executes nearest neighbor queries by passing float arrays directly to your Qdrant database via this MCP Server. When using Gemini's million-token context window, your Google ADK agent can ingest massive documents from BigQuery, convert them, and run deep similarity lookups in a single turn. The Google ADK handles the transport layer, letting you feed these high-dimensional Qdrant search results straight into Vertex AI. This allows your enterprise agent to ground its reasoning in actual vector data without hitting token limits.

Bulk metadata extraction and collection scrolls

The `scroll` tool retrieves Qdrant points along with their payloads to support large-scale data synchronization. Your Google ADK agent can pull batches of vector metadata and feed them into Google Cloud storage or BigQuery for downstream analysis. By combining `scroll` with `get_collection`, the Google ADK agent maps out the structure of your Qdrant database dynamically. Here's the thing: this lets your Gemini models understand the schema of your indices before writing complex queries.

Direct index inspection using this MCP Server

The `count` tool returns the total number of points in a Qdrant collection to verify data ingestion states. This is critical when your Google ADK pipeline loads millions of vectors from GCP and you need to verify the upload completed. Your Google ADK agent can also run `list_collections` to discover available Qdrant indices on the fly. It gives your Gemini models a clear map of your database structure, ensuring they query the correct collections during multi-step reasoning tasks.

Setup guide

Set up Qdrant MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Qdrant tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Qdrant_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Qdrant tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Qdrant. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Qdrant now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Qdrant MCP in Google ADK

The agent passes a JSON array of floats representing your query vector to the Qdrant `search` tool. Google ADK routes this request to your database and returns the nearest neighbor matches. You can then feed these results directly into Gemini's context window for grounded generation.

Yes, you can use the `count` tool to get the exact number of active points in a Qdrant collection. This is useful for verifying that data pipelines from BigQuery have finished indexing. The Google ADK handles the response format so your Gemini agent can use the metric in its logic.

You use the `scroll` tool to paginate through Qdrant points and retrieve their payload data. This is ideal when Gemini needs to process a large volume of metadata that exceeds standard search limit sizes. The Google ADK returns the points in manageable chunks to prevent memory issues.

The agent will execute the `delete` tool using the point IDs you provide to remove them from the Qdrant collection via the MCP connection. Since this action is irreversible, you should restrict tool access in your Google ADK configuration if you want to prevent accidental data loss.

Your Qdrant collection metadata and point IDs are processed entirely within an ephemeral V8 sandbox. Vinkius secures the connection between Google ADK and your database endpoint using a single secure token. Your raw vector payloads are never exposed to external training loops.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript