How to Use the Placetel MCP in LangChain

Q: Can a LangChain agent query Placetel SIP users and active calls in one run?

Yes, the agent can chain these queries together. It runs listsipusers first, then uses listcalls to match active sessions against those specific accounts in a single execution loop.

Run multi-step VoIP chains using LangChain to read Placetel call logs and manage SIP users dynamically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Placetel MCP to LangChain

Create your Vinkius account to connect Placetel to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Placetel with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Placetel lookups in LangChain

The `list_users` tool lets your agent find active team members before checking their hardware configurations. When a call drops, the agent runs this lookup and feeds the resulting user ID directly into `list_devices` to pinpoint the offline desk phone. LangChain manages this sequence as a logical pipeline, passing JSON payloads from one step to the next without manual parsing. You get clean LangSmith traces for every MCP tool execution, showing you exactly how the agent resolved the user's hardware status.

Trace call history via LangSmith

The `list_call_detail_records` tool extracts raw telecom metrics directly into your LangGraph agent state. By feeding these records into a decision loop, your agent can flag spikes in dropped calls or track billing anomalies over the last billing cycle. Instead of guessing why a run failed, you see the exact payload returned from the Placetel platform in your LangSmith dashboard. This visibility lets you debug chain latency and token usage when processing thousands of telecom logs.

Automated group routing with this MCP Server

The `get_group` tool pulls membership lists to help your LangChain agent audit call queues and routing profiles. It reads the current queue structure, then uses `list_sip_users` to verify if the assigned agents are actually online and registered. This setup turns your static communication setup into a dynamic, agent-driven router. Your agent checks active calls with `list_calls` and updates its internal state based on who is currently talking.

Setup guide

Set up Placetel 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 Placetel 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({
    "placetel-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 Placetel 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 Placetel. 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 Placetel 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 Placetel MCP in LangChain

You don't pass API keys directly to the framework. Vinkius handles the authentication securely in its sandbox, giving your LangChain client a single secure endpoint token to access the MCP server.

Yes, the agent can chain these queries together. It runs `list_sip_users` first, then uses `list_calls` to match active sessions against those specific accounts in a single execution loop.

The framework catches the API error and passes the raw error message back to your agent. This lets the agent decide whether to retry the lookup or try a different tool like `list_users` to find the data.

You configure tool access directly when initializing your MCP client. Simply pass a filtered list of tools, such as only allowing `list_calls` and `list_numbers`, during setup.

All call logs, SIP configurations, and user details are processed inside ephemeral V8 isolates. No data is stored on Vinkius servers, and the connection closes immediately after the tool execution completes.

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