How to Use the Qdrant MCP in LangChain

Q: Can LangChain handle Qdrant collection listing?

Yes. You simply register the listcollections tool with your agent. It will query your instance and return a list of available collections for further inspection.

Q: Does Qdrant integrate with LangChain for point deletion?

It does. You can allow your agent to call delete to remove specific points. Be careful, as this action is irreversible and affects your data immediately.

Connect Qdrant to LangChain agents for precise vector retrieval and automated collection management in your reasoning chains.

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 LangChain

Create your Vinkius account to connect Qdrant to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain similarity searches in LangChain

Trigger `search` operations directly from your agent flow. Your chain receives the top-k vectors, allowing subsequent nodes to process the payload immediately. This bypasses manual data handling. You feed the output of one tool call into the next step of your chain without writing custom glue code.

Manage Qdrant collections programmatically

Use `list_collections` and `get_collection` to inspect your database state during runtime. This gives your agent the context needed to select the correct index for a task. Verification happens inside the chain. If a collection is missing or misconfigured, the agent detects the state and reports it back to your LangSmith trace.

Automated point retrieval for agents

Pull specific records using `get_points` or iterate through indexes with `scroll`. Your agent can now reconcile live database data against its current context window. This keeps your reasoning grounded. The agent fetches only what it needs, keeping token usage efficient and responses accurate.

Setup guide

Set up Qdrant MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Qdrant tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "qdrant-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Qdrant transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You initialize the Qdrant MCP server via the adapter and pass the tools to your agent. The agent then invokes the `search` tool with your vector query, returning results directly into the execution chain.

Yes. You simply register the `list_collections` tool with your agent. It will query your instance and return a list of available collections for further inspection.

It does. You can allow your agent to call `delete` to remove specific points. Be careful, as this action is irreversible and affects your data immediately.

Use LangSmith tracing. Every tool call made by the server is logged as a distinct step, showing you exactly what inputs were sent and what payloads were returned.

All traffic stays between your local instance and your agent. This MCP server touches only your vector data and payload objects, using standard authentication headers to secure the connection.

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