How to Use the 8x8 Work MCP in Google ADK

Q: How do I add 8x8 Work tools to a Google ADK agent?

You'll use the McpToolset from the Google ADK library, pointing it to your Vinkius server URL. Then, you pass this toolset into the tools parameter when you initialize your LlmAgent. You can also use toolnames to filter which specific tools are exposed.

Connect Google ADK agents to 8x8 Work to analyze call data alongside your other Google Cloud services.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 8x8 Work MCP to Google ADK

Create your Vinkius account to connect 8x8 Work 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 8x8 Work with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Call Records Like a Database

Your Gemini agent gets direct API access to your company's phone logs through the `list_call_records` tool. It can fetch raw call data based on dates, times, or other filters you specify. Think of it as giving your agent a queryable view into your communications history. This gets really powerful when you're already on Google Cloud. Your agent can pull call records from 8x8 Work, then use a native Google ADK tool to cross-reference that data with customer information in BigQuery. You can finally link call activity to real business outcomes stored in your own tables.

Monitor Ring Groups with Gemini

Use the `list_ring_groups` tool to have your agent track call queue metrics. It can pull current stats for any ring group, like total calls, answered calls, and wait times, giving you an operational overview directly in your agent's context. Here's the thing about using Gemini: its huge context window is a major advantage. An agent can pull weeks of ring group analytics using this MCP Server, hold all of it in memory, and identify subtle, long-term performance trends that smaller models would completely miss.

Build Enterprise Agents with this MCP Server

The `get_extension_summary` tool lets an agent report on individual or team performance. You can build internal tools where managers ask the agent for a specific employee's call stats, and it gets the data straight from the source. Google ADK is designed for building agents that are deeply integrated into your company's infrastructure. By adding this 8x8 Work connection, your agent isn't just a smart assistant; it's a core part of your operations on Google Cloud, with direct access to your communication platform's data.

Setup guide

Set up 8x8 Work 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 8x8 Work 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="8x8 Work_agent",
    model="gemini-2.0-flash",
    instruction="You have access to 8x8 Work 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 8x8 Work. 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 8x8 Work 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 8x8 Work MCP in Google ADK

You'll use the `McpToolset` from the Google ADK library, pointing it to your Vinkius server URL. Then, you pass this toolset into the `tools` parameter when you initialize your `LlmAgent`. You can also use `tool_names` to filter which specific tools are exposed.

Yes, that's a primary use case. Your agent can use the 8x8 Work MCP toolset to get call logs and the native Google ADK toolset to query BigQuery. The agent can then reason over both sets of data to answer complex questions.

It means your agent can analyze much larger amounts of data at once. You can ask it to review a full month of call records from `list_call_records` to find patterns, something that would require multiple calls and complex state management with other models.

Absolutely. The framework supports both HTTP and Stdio transports, so it's flexible enough to run in a serverless function, a container, or a headless script as part of an automated pipeline.

The server only processes your 8x8 Work call detail records (CDRs), ring group statistics, and extension summaries. Your Vinkius endpoint token authenticates the connection, but the server itself is stateless and ephemeral. It doesn't store your call data after the request is complete.

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