How to Use the Redis Vector MCP in LangChain

Q: How do I perform a KNN search using Redis Vector with LangChain?

Pass the searchvectors tool to your agent definition. Provide your query vector as a JSON array of floats, and the agent handles the similarity request.

Q: Can LangChain agents create a new Redis Vector index automatically?

Yes. Simply include createvectorindex in your tool set. The agent will trigger index creation whenever your logic dictates a new schema is required.

Build complex LangChain reasoning chains that push and pull vector embeddings directly from your Redis instance.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Redis Vector MCP to LangChain

Create your Vinkius account to connect Redis Vector 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 Redis Vector with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chainable Redis Vector operations

Your agent uses `upsert_vector` to push embeddings into your Redis stack as part of a multi-step execution chain. LangChain treats these tool calls as nodes, allowing the agent to persist state between steps. Running `search_vectors` lets the chain retrieve context based on KNN similarity. You gain full observability in LangSmith for every transaction.

Dynamic index management for LangChain

Automate your infrastructure by calling `create_vector_index` within a ReAct loop. The agent adjusts dimensions and configurations on the fly based on incoming data requirements. Use `list_indexes` and `get_index_info` to audit your environment. The agent makes decisions on which index to target without manual intervention.

Direct document control via MCP

Clean up your database by invoking `delete_vector` when an agent identifies stale records. This keeps your search results accurate and your memory usage predictable. This MCP Server provides the granular control needed for high-performance pipelines. Every operation is logged and traceable through your standard development tools.

Setup guide

Set up Redis Vector 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 Redis Vector 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({
    "redis-vector-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 Redis Vector 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 Redis Vector. 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 Redis Vector 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 Redis Vector MCP in LangChain

Pass the `search_vectors` tool to your agent definition. Provide your query vector as a JSON array of floats, and the agent handles the similarity request.

Yes. Simply include `create_vector_index` in your tool set. The agent will trigger index creation whenever your logic dictates a new schema is required.

It functions perfectly with persistent sessions. Use the client session to maintain context while the agent performs multiple vector operations in sequence.

LangChain catches the error and reports it in your trace. You can then build retry logic or fallback paths into your agent's reasoning process.

Your vector data never leaves the encrypted tunnel provided by the Vinkius sandbox. Only authorized tokens can trigger index modifications or document deletions.

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