How to Use the Uniphore Conversation AI MCP in AutoGen

Q: How do I find relevant meetings using Uniphore Conversation AI and AutoGen?

Use listmeetings to get a pool of IDs. Then, deploy two agents: one to filter the list based on criteria, and another to confirm the filtered set is complete.

Q: Can I compare summaries using Uniphore Conversation AI and AutoGen?

Yes. You can pass multiple meeting IDs to getmeetingsummary. Then, have an agent group debate which summary is most useful or if they contradict each other.

Q: What if I need action items from Uniphore Conversation AI and AutoGen?

An agent can call getactionitems for several meetings. A second agent then debates which of those action items are the highest priority or most urgent.

Q: Does Uniphore Conversation AI support getting transcripts with AutoGen?

The gettranscript tool provides the raw data. You can set up a 'Legal Agent' and have it review the transcript against compliance rules, flagging specific sections for deliberation.

Drive consensus decisions by debating Uniphore Conversation AI data with AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Uniphore Conversation AI MCP to AutoGen

Create your Vinkius account to connect Uniphore Conversation AI 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 Uniphore Conversation AI with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate meeting content using MCP Server

The `get_meeting` tool fetches a specific meeting's core details. You can set up multiple agents—say, a 'Compliance Agent' and a 'Speed Agent'—to debate the suitability of that meeting based on its metadata. The process is consensus-driven: one agent pulls the data, another checks it against internal policies, and a third determines the final risk score.

Challenge analytics with AutoGen

Want to verify if reported metrics are accurate? One agent uses `get_meeting_analytics` to pull stats. A second 'Skeptic Agent' then challenges those numbers by cross-referencing the raw data pulled from the `get_transcript` tool. This deliberation process forces a deeper review of the data than simple API calls allow.

Synthesize findings with MCP Server

Use the `search_meetings` tool to gather several potential meetings. Then, deploy an agent group where one 'Researcher' reviews all the search results and passes them to a 'Synthesis Agent.' This final agent writes a single, reasoned conclusion. The answer isn't obvious; it requires multiple perspectives debating the compiled data.

Setup guide

Set up Uniphore Conversation AI 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 Uniphore Conversation AI 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="Uniphore Conversation AI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Uniphore Conversation AI 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="Uniphore Conversation AI_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Uniphore Conversation AI 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 Uniphore. 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 Uniphore Conversation AI 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 Uniphore Conversation AI MCP in AutoGen

Use `list_meetings` to get a pool of IDs. Then, deploy two agents: one to filter the list based on criteria, and another to confirm the filtered set is complete.

Yes. You can pass multiple meeting IDs to `get_meeting_summary`. Then, have an agent group debate which summary is most useful or if they contradict each other.

An agent can call `get_action_items` for several meetings. A second agent then debates which of those action items are the highest priority or most urgent.

The `get_transcript` tool provides the raw data. You can set up a 'Legal Agent' and have it review the transcript against compliance rules, flagging specific sections for deliberation.

This server touches meeting metadata and conversation transcripts. By using AutoGen, multiple agents can review the data together, ensuring that compliance is checked from several perspectives before a decision is made.

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