How to Use the 8x8 Work MCP in OpenAI Agents SDK

Q: How does the 8x8 Work MCP Server connect to the OpenAI Agents SDK?

You instantiate the MCPServerStreamableHttp class with your Vinkius endpoint URL. Then you just pass that server object into the mcpservers list when you create your agent. The agent discovers the tools automatically.

Q: Is there a performance cost when using 8x8 Work with the OpenAI Agents SDK?

For best performance, set cacheToolsList=True when creating your server object. This caches the available tools from the MCP Server after the first call, so subsequent requests are faster and don't need to re-fetch the tool list.

Give your OpenAI agents direct access to audit 8x8 Work call logs, ring group stats, and extension performance.

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 OpenAI Agents SDK

Create your Vinkius account to connect 8x8 Work to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Call Detail Records

Connect your agent to `list_call_records` and it can pull phone logs on demand. You can ask it to find all calls from a specific number, check call durations during a certain time frame, or flag unanswered calls. Because you're using the OpenAI Agents SDK, every action is logged. The built-in tracing gives you a full audit trail in the OpenAI dashboard, so you can see exactly which records your agent accessed and why. This isn't a black box; it's a production-ready tool for your team.

Analyze Ring Group Performance

Your agent can use the `list_ring_groups` tool to get a snapshot of queue performance. It checks stats like the number of calls, how many were answered, and average wait times. It’s a fast way to see if a support or sales queue is keeping up with demand. This is where agent handoffs in the SDK really shine. One specialized agent can monitor ring group stats. If it detects that the abandoned call rate exceeds a set threshold, it can hand off to another agent to create a high-priority ticket or send a manager an alert. It’s a simple way to build an automated monitoring system.

Report on Extension Activity with OpenAI Agents SDK

Give your agent the `get_extension_summary` tool to check performance for any user extension. A manager can just ask, “What was Jane’s call summary for last week?” The agent gets the answer directly from your 8x8 Work account. This MCP Server makes your agent a reliable source for business data. The SDK's guardrails can prevent agents from taking unintended actions, adding a layer of safety before any tool is executed. You get the data you need, with the control you expect for a deployed application.

Setup guide

Set up 8x8 Work MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all 8x8 Work tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives 8x8 Work tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate 8x8 Work tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="8x8 Work Agent",
            instructions="You have access to 8x8 Work tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You instantiate the `MCPServerStreamableHttp` class with your Vinkius endpoint URL. Then you just pass that server object into the `mcp_servers` list when you create your agent. The agent discovers the tools automatically.

Yes. The OpenAI Agents SDK allows you to define which tools an agent is permitted to use. You can create specialized agents that only have access to `list_call_records`, for instance, ensuring they can't access other data.

You can build agents that answer specific business questions. For example, ask your agent to 'pull all call detail records from yesterday between 2 PM and 4 PM' or 'check the performance of the main support ring group'.

For best performance, set `cacheToolsList=True` when creating your server object. This caches the available tools from the MCP Server after the first call, so subsequent requests are faster and don't need to re-fetch the tool list.

This server only interacts with your 8x8 Work call data, specifically call detail records, ring group analytics, and individual extension summaries. Vinkius infrastructure is ephemeral and zero-trust, so your data is processed in a temporary, sandboxed environment for each request and never stored.

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