How to Use the 8x8 Work MCP in LangChain

Q: How do I pass 8x8 Work call records into a LangChain agent?

Use the MultiServerMCPClient to connect to this server. Call client.gettools() and pass those tools directly to your LangChain createagent function so it can run listcallrecords natively.

Q: Can I trace 8x8 Work tool execution latency in LangChain?

Yes, absolutely. Every time your agent triggers getextensionsummary or listringgroups, LangSmith traces the input, output, and execution time of that MCP tool call.

Feed 8x8 Work call analytics directly into your LangChain reasoning loops to spot performance bottlenecks instantly.

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 LangChain

Create your Vinkius account to connect 8x8 Work 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 8x8 Work with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain 8x8 Work CDR audits with LangChain agents

Stop pulling manual reports. Run `list_call_records` to feed raw CDR logs straight into a multi-step LangChain agent via MCP. The agent parses call durations, spots anomalies, and passes that output to the next node in your chain without writing custom glue code. You get full observability through LangSmith. If your agent decides to run `get_extension_summary` because a specific sales rep has high talk times, you can trace the exact latency and token cost of that decision in your console.

Trace 8x8 Work ring group trends in LangSmith

Let your LangChain pipeline monitor your inbound 8x8 Work queues. By hooking up `list_ring_groups`, your chain can automatically flag when queue wait times spike. You don't have to build custom alerting dashboards; the MCP Server handles the decision logic. Combining this with the framework's memory tools lets your agent compare today's ring group metrics against last week's performance. It is a direct way to see if your support desk is slipping under load.

Multi-step routing with this MCP Server

Build complex reasoning paths that react to live phone system activity. Your LangChain pipeline can run `get_extension_summary` to check an 8x8 Work rep's status, then instantly route that data to a vector database or an email notification tool using LangChain's vast integration library alongside this MCP setup. This setup turns static phone logs into active triggers. When a high-priority customer hangs up, your chain detects the drop via `list_call_records` and immediately flags the account manager.

Setup guide

Set up 8x8 Work 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 8x8 Work 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({
    "8x8-work-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 8x8 Work 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 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 LangChain

Use the `MultiServerMCPClient` to connect to this server. Call `client.get_tools()` and pass those tools directly to your LangChain `create_agent` function so it can run `list_call_records` natively.

Yes, absolutely. Every time your agent triggers `get_extension_summary` or `list_ring_groups`, LangSmith traces the input, output, and execution time of that MCP tool call.

Yes, it does. You can initialize a persistent session using `client.session()` to let your LangChain agent remember previous call records and ring group analytics across multiple conversation turns.

Your agent should chunk its requests. Instead of pulling everything at once, configure your chain to call `list_call_records` with narrow time filters to avoid hitting API thresholds.

Your 8x8 Work call logs and ring group analytics stay inside a secure, ephemeral V8 isolate sandbox. Vinkius handles your 8x8 Work credentials, meaning your raw phone logs never touch the LLM or get exposed to the client.

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