How to Use the Desku.io MCP in Google ADK

Q: How do I use the Desku.io MCP Server with Google ADK?

Initialize an McpToolset using the StreamableHttpServerParameters class and your Vinkius URL. Pass that toolset into your LlmAgent configuration. The framework handles the HTTP transport automatically.

Q: Can Google ADK create new Desku.io tickets?

Yes. The agent uses the createticket tool to open a new issue. It can populate the subject, description, and assign it to a specific user.

Q: How do I filter Desku.io tools in Google ADK?

You pass a list of strings to the toolnames parameter when setting up the toolset. This restricts the agent to specific actions like listcustomers while blocking write operations.

Give Google ADK agents direct read and write access to your Desku.io support desk.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Desku.io MCP to Google ADK

Create your Vinkius account to connect Desku.io 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 Desku.io with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed massive ticket histories to Gemini

Gemini models eat context for breakfast. You can pull thousands of past interactions using `list_tickets` and dump them straight into the model's massive token window. The Google ADK agent parses the entire dataset to find recurring bugs. Finding a specific user issue takes seconds. The agent runs `get_customer` to grab their profile, then cross-references that with your internal BigQuery tables. It connects the support request to actual product usage metrics.

Desku.io MCP Server automated triage

New tickets need immediate categorization. Your Google Cloud agent detects a new submission and fires `get_ticket` to read the subject line and initial description. It evaluates the severity based on your Vertex AI custom logic. Updating the system happens without human intervention. The agent executes `update_ticket` to tag the issue, assign a priority, and route it. If it needs to alert a specific team member, it checks `list_agents` first.

Draft and send replies natively

Reading data is only half the job. Enterprise agents need to close loops. When a user asks for an update, the agent checks the status and uses `create_conversation` to post a reply back into the thread. Creating new issues works the exact same way. If an internal system fails, your agent can run `create_ticket` to alert the support team proactively. You restrict which tools it can access using the `tool_names` filter in the `McpToolset` setup.

Setup guide

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

Initialize an `McpToolset` using the `StreamableHttpServerParameters` class and your Vinkius URL. Pass that toolset into your `LlmAgent` configuration. The framework handles the HTTP transport automatically.

Yes. The agent uses the `create_ticket` tool to open a new issue. It can populate the subject, description, and assign it to a specific user.

You pass a list of strings to the `tool_names` parameter when setting up the toolset. This restricts the agent to specific actions like `list_customers` while blocking write operations.

They pair perfectly. You can pull extensive thread data via `list_conversations` and let Gemini analyze the entire history at once. The model easily digests months of back-and-forth dialogue.

We isolate every request in an ephemeral V8 environment. When your agent fetches raw chat logs via `list_conversations`, the sandbox routes the payload securely and then terminates. Your proprietary support transcripts never touch a persistent disk.

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