How to Use the Qdrant MCP in LlamaIndex

Q: What is the best way to execute a search query with Qdrant and LlamaIndex?

You wrap the server tools in an McpToolSpec and pass them to your LlamaIndex agent. When a query requires vector data, the agent invokes search and incorporates the results into its context.

Q: Can LlamaIndex count points in my Qdrant collections?

Yes. Use the count tool to get the total number of points in any collection. This helps the agent decide if it needs to perform a full scan or a targeted search.

Q: How does Qdrant support LlamaIndex data retrieval?

By providing granular access to points via getpoints and scroll. These tools let the agent pull raw payload data into your knowledge base for grounded reasoning.

Build grounded RAG pipelines by linking Qdrant to LlamaIndex for real-time knowledge synthesis.

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 LlamaIndex

Create your Vinkius account to connect Qdrant to LlamaIndex — 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Qdrant data for LlamaIndex

Feed `search` results directly into your knowledge base. This allows your agent to reference live vector data alongside your existing documents. It removes the gap between your search results and your final answer. The data becomes a primary source of truth for every query the agent generates.

Dynamic collection inspection in LlamaIndex

Use `get_collection` to verify index properties before starting a retrieval task. This ensures your agent operates on the correct vector dimensions. It prevents runtime errors during query execution. Your agent checks the metadata first, then proceeds with the search operation.

Iterate over large sets using LlamaIndex

The `scroll` tool allows your agent to process large batches of points without overloading memory. It is ideal for building comprehensive knowledge graphs from your existing database. Pagination is handled by the tool. Your agent requests segments, processes the payloads, and continues until the entire collection is indexed.

Setup guide

Set up Qdrant MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Qdrant MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Qdrant tools.",
)
response = await agent.run("List recent Qdrant data")

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 LlamaIndex

You wrap the server tools in an `McpToolSpec` and pass them to your LlamaIndex agent. When a query requires vector data, the agent invokes `search` and incorporates the results into its context.

Yes. Use the `count` tool to get the total number of points in any collection. This helps the agent decide if it needs to perform a full scan or a targeted search.

By providing granular access to points via `get_points` and `scroll`. These tools let the agent pull raw payload data into your knowledge base for grounded reasoning.

You only need the endpoint token for your Vinkius-managed server. Once connected, your agent has full access to the tools you choose to expose.

Your vector values and associated metadata are transmitted over an encrypted channel. The server only accesses the specific points requested by the agent during the RAG process.

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