How to Use the Azure Cosmos DB Container MCP in LangChain

Q: How do I connect Azure Cosmos DB Container to LangChain?

Install langchain-mcp-adapters in your environment. Pass your Vinkius endpoint to MultiServerMCPClient and fetch the tools for your agent.

Q: What SQL format does the query tool expect?

Cosmos DB NoSQL syntax. You write statements against the c alias without specifying the database or container names in the query string itself.

Build multi-step reasoning pipelines with LangChain that read and write directly to your Azure NoSQL backend via this MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Azure Cosmos DB Container MCP to LangChain

Create your Vinkius account to connect Azure Cosmos DB Container 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 Cosmos DB Container with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain document actions in LangChain

This MCP Server gives your LangChain agents direct access to Azure Cosmos DB NoSQL operations. You bind the `create_document` and `get_document` tools to your LLM, letting it handle state persistence mid-chain. Complex agents need memory. When your ReAct agent evaluates a user request, it calls `query_documents` to pull existing records, decides what needs updating, and pushes the new JSON right back. LangSmith tracks every tool input and output so you see exactly what database calls your agent made.

Execute raw SQL with the MCP Server

The `query_documents` tool accepts raw Cosmos SQL syntax like "SELECT * FROM c WHERE c.status = @status" straight from your agent. Your pipeline doesn't need custom ORM wrappers or hardcoded endpoints. Passing parameters as JSON means your LangChain tools stay safe from injection vectors. The agent decides which partition keys matter based on the context, pulls the filtered subset, and passes that exact payload down to the next node in your graph.

Manage lifecycles automatically

Call `delete_document` right from a cleanup node in your LangGraph workflow. Providing the required partition key guarantees you only drop the specific record you targeted. Combining these four operations turns a static agent into a full CRUD application. The MCP multi-server aggregation lets you mix this Cosmos connection with other API endpoints in the exact same LangChain sequence.

Setup guide

Set up Azure Cosmos DB Container 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 Cosmos DB Container 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-cosmos-db-container-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 Cosmos DB Container 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 Cosmos DB Container. 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 Cosmos DB Container 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 Cosmos DB Container MCP in LangChain

Install `langchain-mcp-adapters` in your environment. Pass your Vinkius endpoint to `MultiServerMCPClient` and fetch the tools for your agent.

Yes, LangSmith handles full observability for these tool calls. You see the exact SQL strings the agent sent and the JSON payloads returned.

They can if you expose that specific tool. You control which endpoints the agent sees during the `create_agent` setup phase.

Cosmos DB NoSQL syntax. You write statements against the `c` alias without specifying the database or container names in the query string itself.

Vinkius runs this connection inside an ephemeral V8 Isolate Sandbox. Your Cosmos DB JSON documents and partition keys pass directly to your agent without touching persistent storage. The zero-trust architecture tears down the environment the second your chain finishes executing.

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