How to Use the Azure DevOps MCP in Google ADK

Q: How can I use Google ADK to create a report on all Azure DevOps work items?

Instruct your Gemini agent to use the listworkitems tool for each project. Because Google ADK integrates with BigQuery, you can have the agent collect the results and save them to a table for later analysis.

Q: What's the best way to get started with Google ADK and this Azure DevOps server?

Install google-adk and create an McpToolset instance pointing to your Vinkius URL. Pass that toolset to your LlmAgent. You can use the toolnames filter to expose only specific tools, like listbuilds, to start.

Connect Gemini to your Azure DevOps data with Google ADK. Build agents that reason over your entire software development lifecycle.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Azure DevOps MCP to Google ADK

Create your Vinkius account to connect Azure DevOps 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 DevOps with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Reason Across All Projects

This toolset feeds your Gemini agent a complete view of your organization. The agent can call `list_projects`, `list_repositories`, and `list_pipelines` for every single project you have. It's the raw data feed for high-level analysis. This is why you use Google ADK. Gemini's huge context window lets the agent hold all that data at once. It can answer complex questions like, 'Which projects have no deployment pipelines configured?' without losing track. This goes way beyond simple lookups.

Analyze DevOps Metrics with this MCP Server

Give your agent the power to pull raw DevOps data for analysis. It can use `list_builds` to get historical build outcomes and `list_work_items` to get a snapshot of the current backlog. With Google ADK, you can pipe this data straight into BigQuery. An agent can run a daily job to fetch build stats, load them into a table, and then use Vertex AI to find trends in build failures. You're not just asking questions; you're building an automated DevOps analyst on Google Cloud.

Get a Handle on Team Structure

Your agent can map out your entire org chart. It uses `list_project_teams` to see who is on which project. This is the first step to automating any kind of resource management. Imagine an agent built with Google ADK that cross-references this team data with your GCP IAM policies. It can identify which teams have access to which cloud resources or flag projects that are missing key personnel. This MCP Server provides the foundational DevOps data for that kind of enterprise-level reasoning.

Setup guide

Set up Azure DevOps 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 DevOps 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 DevOps_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Azure DevOps 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 DevOps. 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 DevOps 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 DevOps MCP in Google ADK

Instruct your Gemini agent to use the `list_work_items` tool for each project. Because Google ADK integrates with BigQuery, you can have the agent collect the results and save them to a table for later analysis.

Yes, that's a common pattern. You can deploy your Gemini agent as a Cloud Function, triggered on a schedule, to perform checks on your Azure DevOps organization using this MCP Server.

Install `google-adk` and create an `McpToolset` instance pointing to your Vinkius URL. Pass that toolset to your `LlmAgent`. You can use the `tool_names` filter to expose only specific tools, like `list_builds`, to start.

Google ADK is designed for the Gemini family of models. It's built to take advantage of their long-context capabilities and tight integration with the Google Cloud ecosystem.

This server reads metadata: project names, team lists, build history, and work item summaries. It doesn't touch your code or secrets. Each connection is authenticated with a unique Vinkius token, and all processing happens in isolated, single-use environments that are destroyed after your request.

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