How to Use the JustCall MCP in LangChain

Q: Can LangChain agents read SMS replies in JustCall?

Yes. Your agent calls listmessages to pull text content, sender details, and delivery status. It can then parse those texts to trigger downstream actions in your chain.

Q: Does this server support audio transcription?

The server itself provides access to the audio files via listrecordings. You must pass those recording URLs into a separate LangChain transcription tool to extract the text.

Build multi-step communication pipelines by connecting LangChain agents directly to your JustCall data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect JustCall MCP to LangChain

Create your Vinkius account to connect JustCall 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 JustCall with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain JustCall MCP Server Operations

LangChain thrives on connecting inputs to outputs using endpoints like `get_contact`. You can build a ReAct agent that pulls a specific customer record and immediately feeds that ID into `list_calls` to build a complete interaction history. The agent decides what to query next based on the previous step's output. Full observability via LangSmith means you track exactly how many tokens your agent burns while iterating through `list_campaigns`. If a chain fails mid-execution, you see exactly which tool call dropped the ball. Your agent strings together these JustCall endpoints to automate complex auditing tasks without human intervention.

Audit Agent Activity

You can wire a LangChain pipeline to pull active team members via `list_users` and cross-reference their IDs against audio logs. Support managers waste hours matching phone logs to agent schedules manually. The chain runs the `list_recordings` output through a transcription model and generates a formatted QA report. This replaces manual dashboard clicking with automated reasoning. Your agent queries `list_numbers` to map inbound lines to specific campaigns, then checks `list_messages` to see if the team actually followed up via SMS. LangChain handles the control flow while the MCP endpoints provide the raw communication data.

Monitor Telemarketing Health

You can set up a LangGraph node that polls `list_campaigns` every hour to check status changes. Outbound dialer campaigns generate massive amounts of data that usually sit unread. If a campaign stalls, the agent triggers `get_call` on the last few dialed numbers to investigate participant timestamps and notes. The real value here is reactive decision making. LangChain evaluates the call duration and status from `list_calls` against your predefined success metrics. It then formats a slack alert detailing exactly why the campaign underperformed, citing specific JustCall tool outputs as evidence.

Setup guide

Set up JustCall 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 JustCall 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({
    "justcall-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 JustCall 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 JustCall. 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 JustCall 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 JustCall MCP in LangChain

Install the langchain-mcp-adapters package first. Then initialize a MultiServerMCPClient pointing to the JustCall server URL and pass the resulting tools into your ReAct agent.

Yes. Your agent calls `list_messages` to pull text content, sender details, and delivery status. It can then parse those texts to trigger downstream actions in your chain.

Scripts break when edge cases happen. A LangChain agent dynamically decides to run `get_contact` if a phone number from a call log lacks an existing CRM record.

The server itself provides access to the audio files via `list_recordings`. You must pass those recording URLs into a separate LangChain transcription tool to extract the text.

The MCP server runs in a zero-trust V8 Isolate Sandbox on Vinkius. When your agent pulls SMS content and call notes, that data flows directly to your client over an ephemeral connection. Vinkius drops the state the moment the session ends.

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