How to Use the Azure AI Search MCP in LangChain

Chain Azure AI Search tools directly into your LangChain agent pipelines for multi-step data reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Azure AI Search MCP to LangChain

Create your Vinkius account to connect Azure AI Search to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Azure AI Search with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sequence Azure AI Search calls in LangChain

Feed the output of `search_documents` directly into subsequent chain tasks. You define the logic where one tool result determines the next step in your sequence. LangSmith traces every step of these MCP tool calls. You keep full visibility into latency and token consumption while your agent navigates search configurations.

Map vector data across LangChain nodes

Use `vector_search` to pull relevant embeddings into your reasoning chain. It forces the agent to handle specific dimensional maps as part of your broader data architecture. This MCP server fits into your existing LangGraph workflows without extra boilerplate. You pass the tools into your agent and let the state-machine decide the execution order.

Query index metadata via LangChain

Call `get_index` or `list_indexes` to verify your cloud configuration before running search tasks. You avoid blind queries by checking the index state first. Your agent inspects the environment through these tools to adjust its search strategy. It keeps your pipeline context aware of current Azure AI Search deployments.

Setup guide

Set up Azure AI Search 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 Azure AI Search 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({
    "azure-ai-search-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 Azure AI Search 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 Azure AI Search. 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 Azure AI Search 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 Azure AI Search MCP in LangChain

Register the server tools using the MCP adapter and pass them into your agent constructor. The agent then selects `search_documents` whenever the prompt requires external cloud data.

Yes, LangSmith captures every input and output for these tools. You see the exact query sent to your index and the raw response from the cloud.

You can aggregate this with other servers using the MultiServerMCPClient. It allows your agent to pull data from Azure AI Search and other sources in a single chain.

The client treats your index data as standard tool output. Vinkius secures the connection, and the data stays within your defined execution flow.

Your index definitions and search results never leave your local session or authorized environment. The server only transmits the specific index parameters requested during your active agent tasks.

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