How to Use the Uniphore Conversation AI MCP in LangChain

Q: How do I search meetings using Uniphore Conversation AI and LangChain?

Start by calling listtopics to identify relevant keywords. Then, use those keywords directly in the searchmeetings tool. The agent handles this multi-step process automatically.

Q: Can I get meeting summaries using Uniphore Conversation AI and LangChain?

Absolutely. After finding a meeting ID with listmeetings, you can pass that ID to the getmeetingsummary tool. This gives you the AI-generated summary, which your agent then processes for next steps.

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

The dedicated getactionitems tool extracts specific tasks. You simply pass the target meeting ID to this function, and it returns a structured list of required actions.

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

Yes. The gettranscript tool provides the full text log of any given call. You pass the meeting ID to this function, and it returns the complete raw transcript for your chain.

Build multi-step reasoning agents for Uniphore Conversation AI using LangChain.

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 LangChain

Create your Vinkius account to connect Uniphore Conversation AI to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate complex workflows with MCP Server

The `get_meeting` tool fetches specific meeting details by ID. Then, you can immediately pass that ID to the `get_transcript` tool to pull the raw text. This allows your agent chain to read the transcript and feed it into a subsequent parsing step. Your ReAct agents decide which tools run when. They don't just call one function; they build a sequence, using the output of `list_meetings` as input for `search_meetings`, then passing those results to `get_action_items`.

Analyze conversations in chains with LangChain

The `get_meeting_analytics` tool provides conversation insights, but the chain can do more. You pull the raw data using `get_meeting_analytics`, and then use another step to call `get_meeting_summary` on that specific ID. The agent compares the statistical metrics against the qualitative summary. Because LangChain manages the state, you keep track of everything. If one tool fails or returns partial data, the chain knows how to handle it and continue processing.

Discover topics across multiple servers with MCP Server

Need to know what's trending? Start by using `list_topics` to see all keywords tracked in your organization. Then, you can use the returned topic list to run a targeted search via `search_meetings`. The agent uses this discovered data point to narrow down potential meetings. This sequential process is key: the output of listing topics directly dictates the parameters for searching the meeting database.

Setup guide

Set up Uniphore Conversation AI MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Uniphore Conversation AI tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "uniphore-conversation-ai-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Uniphore Conversation AI transactions"
    })
    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 LangChain

Start by calling `list_topics` to identify relevant keywords. Then, use those keywords directly in the `search_meetings` tool. The agent handles this multi-step process automatically.

Absolutely. After finding a meeting ID with `list_meetings`, you can pass that ID to the `get_meeting_summary` tool. This gives you the AI-generated summary, which your agent then processes for next steps.

The dedicated `get_action_items` tool extracts specific tasks. You simply pass the target meeting ID to this function, and it returns a structured list of required actions.

Yes. The `get_transcript` tool provides the full text log of any given call. You pass the meeting ID to this function, and it returns the complete raw transcript for your chain.

This server handles meeting metadata and conversation transcripts. When connecting via LangChain, your agent's actions are logged through LangSmith tracing, ensuring visibility into tool inputs and outputs.

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