How to Use the Five9 QM MCP in AutoGen

Let your agents debate Five9 QM evaluations with AutoGen. Build consensus on agent performance through multi-agent deliberation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Five9 QM MCP to AutoGen

Create your Vinkius account to connect Five9 QM to AutoGen 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 Five9 QM with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate Five9 QM scores in AutoGen

Deploy a team of agents where one agent uses `list_qm_interactions` to identify issues and another agent uses `create_evaluation` to propose a score. They can challenge each other until they reach a consensus. This setup prevents biased evaluations. By requiring your agents to debate the evidence, you ensure that every score is vetted before it hits your production records.

Cross-reference evaluations with AutoGen

Use `list_calibrations` to feed human-led feedback into your agent's decision loop. Your agents can compare their AI-generated scores against manual reviews to check for alignment. This creates a self-correcting loop. If the agents disagree, they can escalate the interaction to a human supervisor for a final look, ensuring higher accuracy.

Manage Five9 QM users with agent teams

Assign one agent to audit `list_qm_users` while another agent prepares the `get_qm_summary` report. They can coordinate tasks to generate comprehensive performance audits in minutes. This divides the labor effectively. Each agent focuses on a specific aspect of your quality management stack, speeding up your reporting cycle.

Setup guide

Set up Five9 QM MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Five9 QM tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Five9 QM_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Five9 QM data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Five9 QM_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Five9 QM data")
    print(result.messages[-1].content)

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 Five9 QM. 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 Five9 QM 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 Five9 QM MCP in AutoGen

You pass the MCP tools to your AssistantAgent constructor. The adapter handles the schema mapping, allowing your agents to call Five9 functions as if they were native Python commands.

Yes, by setting up a group chat, you can have one agent propose an evaluation based on the interaction data while another critiques it. They will continue the conversation until they agree on the final result.

The tools are fully compatible with multi-agent orchestration. You can define specific roles for your agents, such as a reviewer or a reporter, and grant them access to the required tools.

All communication between your agents and the Five9 API occurs over a secure, authenticated tunnel. No data is shared with other agents or external systems outside your controlled environment.

The server only exposes the specific interaction metadata requested by your agents. Your system remains private, and you retain full control over which agents can access sensitive call records.

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