How to Use the BasicOps MCP in Google ADK

Q: Can I filter the BasicOps tools for my Gemini agent via Google ADK?

Yes, the McpToolset constructor accepts a toolnames argument. Just provide a list of the exact tool names you want to expose, like 'gettask', 'listprojecttasks', to create a limited-scope agent.

Put Gemini agents to work on your BasicOps projects. A direct connection for your agent running on Google Cloud with the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BasicOps MCP to Google ADK

Create your Vinkius account to connect BasicOps 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 BasicOps with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect BigQuery to Your Projects

This setup connects your Google Cloud data directly to your project management. Your Gemini agent can monitor a table in BigQuery, and when a new entry appears—like a new client—it can automatically run `create_project` in BasicOps. No more manual data entry. This works the other way, too. An agent can use `list_projects` to pull all your active project names from BasicOps and write them back to a BigQuery table for long-term analysis. It turns BasicOps into another data source for your enterprise stack.

Analyze Projects with Long Context

Gemini's 1M token context window changes how agents can reason about your work. Instead of looking at one task at a time, an agent can pull an entire project's history using `list_project_tasks` and `list_task_messages` in a single prompt. It sees the whole picture. Use this to build agents that generate truly insightful summaries. They can spot bottlenecks, identify overworked team members, or find tasks that are falling behind, all because they can hold the full context of a project. This isn't just fetching data; it's understanding it.

Manage Resources with Your MCP Server

The Google ADK lets your agent manage your team's workload in BasicOps. It can get a list of all team members with `list_team_users` and then intelligently assign new work by calling `update_task` with the right user ID. It’s a simple way to automate assignments. You can also filter which tools your agent can access. By passing a `tool_names` list during setup, you can create a specialized agent that can only `get_task` and `list_project_tasks`, but can't create or modify anything. It's a safe way to build read-only agents for reporting.

Setup guide

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

After setup, your Gemini agent can directly call tools like `create_task` and `update_task`. You can ask it in plain language to 'Create a new task for the website redesign project' and the ADK will translate that into the correct tool call.

Yes, the `McpToolset` constructor accepts a `tool_names` argument. Just provide a list of the exact tool names you want to expose, like `['get_task', 'list_project_tasks']`, to create a limited-scope agent.

The server provides the raw data, and Gemini does the work. You can use your agent to call `list_project_tasks` and `list_task_messages` for a large project, feed all that text into the model, and then ask for a high-level summary or analysis.

Build an agent that uses both the native BigQuery tools and this BasicOps MCP toolset. The agent can query BigQuery for information and then use that information to call BasicOps tools like `create_project` or `update_task`.

Your agent interacts with your BasicOps project and task data. Because you're running on Google Cloud, that data can be processed within your existing GCP security perimeter. Vinkius adds to this with a zero-trust architecture, ensuring the MCP server itself is isolated and secure.

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