How to Use the Azure Cosmos DB Container MCP in AutoGen

Give your AutoGen agents the ability to debate, query, and modify Azure Cosmos DB records 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 AutoGen

Create your Vinkius account to connect Azure Cosmos DB Container to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let agents manage Cosmos DB

The MCP `query_documents` tool allows your AutoGen agents to pull active database records into their conversation context. A researcher agent can fetch the raw NoSQL data while a reviewer agent checks it for errors. These agents debate the results before taking action. If the performance agent suggests archiving old records, the security agent verifies the partition keys before anyone is allowed to call `delete_document`.

Create documents via consensus

Calling `create_document` happens only after your agents agree on the exact JSON payload. They construct the document, ensure the ID and partition keys exist, and push it to Azure. This beats standard scripted pipelines because the system catches formatting mistakes dynamically. The MCP adapter automatically translates the schema so your agents know exactly what fields are required.

Read specific MCP Server records

Fetching individual items requires `get_document` and the correct partition key. One agent handles the retrieval while another processes the contents. You set this up by passing the Vinkius endpoint to `StreamableHttpServerParams`. The tools load directly into your `AssistantAgent` constructor, ready for immediate use in the next chat turn.

Setup guide

Set up Azure Cosmos DB Container MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Azure Cosmos DB Container tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Azure Cosmos DB Container_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Azure Cosmos DB Container data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Azure Cosmos DB Container_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Azure Cosmos DB Container data")
    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 AutoGen

Install the MCP extension and use the HTTP server parameters. The adapter handles all schema conversions for your agents automatically.

Yes, you can give the tool list to specific agents in your swarm. A database-admin agent might have write access while others only get read permissions.

The database returns an error, which the agent reads in the chat context. It will usually attempt to rewrite the query and try again without user intervention.

It depends entirely on your specific container setup. If your Azure environment requires it, the agent must include it in the tool call.

Vinkius operates on a strict zero-trust model. The Cosmos DB JSON documents and SQL parameters flow through an ephemeral sandbox that is destroyed after the tool executes. Your data never rests on our infrastructure.

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