How to Use the GitScrum MCP in Google ADK

Q: How do I add the GitScrum MCP toolset to a Google ADK agent?

Import the McpToolset from the SDK and point it to your Vinkius HTTP endpoint. Pass this toolset directly into your agent's tool list during initialization. The Gemini model will immediately see all 16 GitScrum tools.

Q: Can Google ADK analyze GitScrum project metrics over time?

Yes, the agent calls projectstats and workspacestats to gather raw project metrics. You can feed this data directly into Vertex AI or BigQuery to build predictive delivery timelines.

Q: How do Google ADK agents manage user roles within GitScrum?

The agent uses myrole and listprojectmembers to verify who has access to specific boards. This ensures the model only assigns tasks to valid team members who are active in the project.

Q: Can I restrict which GitScrum tools a Google ADK agent can access over MCP?

Yes, you can pass an optional tool name filter to the McpToolset constructor. This lets you restrict the agent to read-only tools like listtasks and block write operations like createworkspace.

Connect GitScrum to your Google ADK pipelines to automate project tracking using Gemini's massive context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GitScrum MCP to Google ADK

Create your Vinkius account to connect GitScrum 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 GitScrum with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise Board Management via Google ADK

The `list_workspaces` and `list_projects` tools expose your entire organizational tree to your Google ADK agent. This MCP integration lets it navigate complex, multi-department project boards and correlate task data with your existing BigQuery datasets. Your agent uses `get_project` to fetch metadata and map dependencies across teams. Gemini's million-token context window digests these deep project hierarchies without losing track of details.

Context-Aware Task Audit via MCP Server

The `list_tasks` and `get_task` tools let your Google ADK agent audit project health directly from your cloud console. It scans thousands of open issues, looking for stale tickets or missing assignments. By querying `list_labels`, the agent categorizes work items based on their actual code changes. You get an automated, clean backlog that matches your actual deployment state.

Automated Workspace Organization

The `create_workspace` and `create_project` tools allow your Google ADK workflows to spin up new environments when a customer signs or a new team onboards. Your agent configures the workspace instantly, setting up standard columns and workflows. It queries `get_me` and `my_role` to ensure the agent has the correct permissions before attempting any write actions. Unauthorized board modifications are completely prevented in your production environment.

Setup guide

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

Import the `McpToolset` from the SDK and point it to your Vinkius HTTP endpoint. Pass this toolset directly into your agent's tool list during initialization. The Gemini model will immediately see all 16 GitScrum tools.

Yes, the agent calls `project_stats` and `workspace_stats` to gather raw project metrics. You can feed this data directly into Vertex AI or BigQuery to build predictive delivery timelines.

The agent uses `my_role` and `list_project_members` to verify who has access to specific boards. This ensures the model only assigns tasks to valid team members who are active in the project.

Yes, you can pass an optional tool name filter to the `McpToolset` constructor. This lets you restrict the agent to read-only tools like `list_tasks` and block write operations like `create_workspace`.

No, your GitScrum credentials, workspace names, and task descriptions are kept strictly within your enterprise VPC boundary. Vinkius processes all MCP tool execution requests in isolated, ephemeral sandboxes. No task data or project metrics are ever used to train public LLMs.

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