How to Use the Azure Cosmos DB Container MCP in Google ADK

Q: How do I restrict the agent to read-only access?

Use the toolnames filter in your ADK toolset configuration. Exclude createdocument and deletedocument to prevent the agent from modifying your container.

Feed massive Cosmos DB datasets directly into your Google ADK agent long-context window using 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 Google ADK

Create your Vinkius account to connect Azure Cosmos DB Container to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Azure Cosmos DB Container data with Google ADK

This MCP Server exposes the `query_documents` tool to your Google ADK agent. Your agent can pull thousands of documents at once, dumping the raw JSON straight into Gemini's million-token context window. You don't have to worry about token limits when loading large collections. The agent analyzes the entire dataset to find trends, using native Google Cloud tools to compare the results against your BigQuery tables.

Write structured JSON outputs back to Azure Cosmos DB

The `create_document` tool lets your Google ADK agent write structured results directly to your container. After processing an enterprise workflow, the agent saves its state as a document without needing an external database driver. You must ensure the agent includes the required ID and partition key in the payload. The ADK framework handles this formatting automatically, ensuring every write conforms to your Cosmos schema.

Read and delete documents during multi-step reasoning

Your agent uses `get_document` and `delete_document` to manage transient data during complex Google ADK runs. It can fetch a configuration file, execute a task, and delete the temporary record when finished. This gives your Gemini-powered agents a persistent scratchpad. They can store intermediate reasoning steps in Azure instead of burning context window tokens on historical state.

Setup guide

Set up Azure Cosmos DB Container MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Azure Cosmos DB Container tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Azure Cosmos DB Container_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Azure Cosmos DB Container tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Use the McpToolset class with the streamable HTTP transport parameters pointing to your Vinkius endpoint. Pass this toolset into your LlmAgent constructor to expose the tools.

Yes, the agent translates the user's intent into a SQL query for the query_documents tool. It formats the parameters as JSON without needing to know your database name.

Yes, the integration supports both HTTP and stdio transport methods. You configure this when initializing your StreamableHttpServerParameters in Python.

Use the tool_names filter in your ADK toolset configuration. Exclude create_document and delete_document to prevent the agent from modifying your container.

Your Azure Cosmos DB connection strings are stored securely in the Vinkius environment, never exposed to Google ADK. Only clean JSON document payloads transit through the secure API tunnel.

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