How to Use the 8x8 Contact Center MCP in OpenAI Agents SDK

Q: How do I connect the 8x8 Contact Center MCP Server to my OpenAI Agents SDK project?

You instantiate an MCPServerStreamableHttp object with your Vinkius endpoint URL. Then you pass it into your Agent constructor in the mcpservers list. The agent discovers the tools automatically.

Q: Can my OpenAI agent use this 8x8 Contact Center integration to modify agent status?

No, the tools are read-only. Your agent can use getrealtimemetrics and listagentinteractions to see what's happening, but it can't change an agent's status, answer calls, or modify queue settings.

Connect your OpenAI Agent to live 8x8 Contact Center data for production-grade support automation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 8x8 Contact Center MCP to OpenAI Agents SDK

Create your Vinkius account to connect 8x8 Contact Center 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 Contact Center with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor Live Operations

The `get_realtime_metrics` tool gives your agent a direct view into your 8x8 contact center. You can build agents that watch key metrics—like agent availability or current wait times—and alert a human manager when service levels are at risk. Because this is the OpenAI Agents SDK, you get built-in guardrails. Your agent can run its own monitoring tasks, but you can be sure it's only reading data, never changing agent states or dropping calls. It's all tracked in your OpenAI dashboard.

Audit Agent Performance History

With `list_agent_interactions`, your agent can pull historical performance data for your team. You can ask it to find all interactions handled by a specific agent in the last month and check their average resolution times. This isn't just for one-off questions. You can build a specialized review agent that runs weekly, flags outlier interactions for manual review, and summarizes its findings. The handoff and tracing features are perfect for this kind of workflow.

Analyze Queues with an MCP Server

Use the `list_queue_metrics` tool to analyze how your queues have performed over time. Your agent can ask for things like peak traffic hours or abandonment rates for a specific queue last quarter and get structured data back. This MCP server handles the connection and authentication to 8x8. Your agent just focuses on the task. Set `cacheToolsList=True` in the SDK, and the tool discovery happens only once, making subsequent calls faster.

Setup guide

Set up 8x8 Contact Center 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 Contact Center tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives 8x8 Contact Center 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 Contact Center 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 Contact Center Agent",
            instructions="You have access to 8x8 Contact Center 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 Contact Center. 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 Contact Center 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 Contact Center MCP in OpenAI Agents SDK

You instantiate an `MCPServerStreamableHttp` object with your Vinkius endpoint URL. Then you pass it into your `Agent` constructor in the `mcp_servers` list. The agent discovers the tools automatically.

No, the tools are read-only. Your agent can use `get_realtime_metrics` and `list_agent_interactions` to see what's happening, but it can't change an agent's status, answer calls, or modify queue settings.

You can generate reports on historical agent performance and queue statistics. For example, your agent can pull data with `list_queue_metrics` and summarize weekly call volume, wait times, and abandonment rates for your main support queue.

No, it's straightforward. Vinkius manages the server, so all you need is the endpoint URL. There's no separate API client to install or custom auth code to write for the 8x8 connection itself.

The server provides read-only access to operational metadata. Your agent can see call resolution stats and queue performance numbers, but not sensitive call content. Every request runs in an ephemeral, zero-trust sandbox managed by Vinkius, and authentication is handled by a single token, keeping your main 8x8 credentials 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