How to Use the Evolio MCP in Google ADK

Q: How to connect Evolio to a Gemini agent using Google ADK?

You instantiate an McpToolset pointing to your Vinkius server URL and pass that to your LlmAgent constructor. The agent automatically discovers and can start calling Evolio tools like listclients.

Q: Does the Evolio MCP Server support filtering tools for Google ADK?

Yes. The Google ADK's McpToolset has a toolnames filter. You can use it to expose only a subset of the 14 Evolio tools to a specific agent, creating role-based access control for your agents.

Q: What happens if the Evolio API is down?

The McpToolset in Google ADK will raise an exception when a tool call fails. You should wrap your agent's calls to tools like getclient in standard try/except blocks to handle connection errors. Run checkevoliostatus first to be sure.

Connect Google ADK to your coaching practice. Let Gemini agents analyze client progress and manage cases with your data in Google Cloud.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Evolio MCP to Google ADK

Create your Vinkius account to connect Evolio 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 Evolio with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Cases Directly from Google Cloud

Give your Gemini agent direct control over your coaching operations. It can use the Evolio toolset to `list_clients`, find the right person, and then `create_case` to start a new coaching engagement. The agent can then `create_task` to set up initial onboarding steps. Because this runs within the Google ADK, your agent can cross-reference this activity with data in BigQuery. This is the power of connecting an MCP Server to your cloud data. For example, it could check a client's payment status in a finance table before creating a new case in Evolio.

Use Long-Context for Client Summaries

Gemini's large context window is a perfect fit here. Your agent can call `get_client`, then `list_cases`, and then `list_tasks_by_case` for every single case a client has ever had. It can even pull file lists with `list_client_files`. Your agent can feed that entire history into a single prompt to generate a deep summary of a client's journey. This isn't just a list of tasks; it's a narrative of their progress over time, ready for a coach to review. This is where an MCP Server integration shines.

Build Enterprise Workflows on Google ADK

The Google ADK is designed for building solid, enterprise-grade systems. You can create an agent that listens to a Google Pub/Sub topic for new client signups, then automatically calls `list_clients` to find them and `create_case` in Evolio. You can filter the tools passed to the `LlmAgent` to enforce permissions. Give a 'reporting' agent read-only access with `get_case` and `list_tasks`, but give an 'admin' agent write access with `update_case` and `create_task`.

Setup guide

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

You instantiate an `McpToolset` pointing to your Vinkius server URL and pass that to your `LlmAgent` constructor. The agent automatically discovers and can start calling Evolio tools like `list_clients`.

Yes, that's a primary use case. Your agent can fetch operational data from Evolio using tools like `list_cases_by_status`. Then it can join that data with business metrics in BigQuery for deeper analysis, all within a single agent workflow.

Yes. The Google ADK's `McpToolset` has a `tool_names` filter. You can use it to expose only a subset of the 14 Evolio tools to a specific agent, creating role-based access control for your agents.

The `McpToolset` in Google ADK will raise an exception when a tool call fails. You should wrap your agent's calls to tools like `get_client` in standard try/except blocks to handle connection errors. Run `check_evolio_status` first to be sure.

The server only processes data related to your Evolio clients, cases, and tasks. It has no access to your Google Cloud environment. Your Vinkius token secures the connection, which runs in an ephemeral, zero-trust sandbox for each 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