How to Use the Aircall MCP in LangChain

Q: Can I monitor Aircall tool latency in LangChain?

Yes, every execution of getcalldetails or listcontacts is tracked inside LangSmith. You get full visibility into token usage, latency, and exact payloads for every phone system action.

Run LangChain agents that route Aircall phone logs and update contacts directly through your production LLM chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aircall MCP to LangChain

Create your Vinkius account to connect Aircall 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 Aircall with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Aircall Contact Creation with LangChain Agent Steps

The `create_contact` tool lets your LangChain agent write new records directly to Aircall when a customer interaction triggers an update. This means your agent processes incoming raw text, extracts details, and instantly commits them without manual data entry. You trace this entire execution path inside LangSmith to see exactly how the tool outputs feed into your next chain link. It keeps your CRM clean and your communication pipeline moving without manual oversight.

Multi-Step Call Routing via LangChain MCP Server Chains

The `get_call_details` and `list_calls` tools expose deep technical call metrics and historical logs to your LangChain routing chains. Your agent inspects these metrics to decide whether to escalate a customer file or assign a follow-up task. By combining these tools with other APIs in your LangGraph setup, you build automated post-call workflows. The agent evaluates the call duration and status, then triggers the next step in your custom chain instantly.

Live Team Availability Checks for LangChain Agents

The `get_user_details` and `list_users` tools supply your LangChain agent with real-time availability states via this MCP server. Your agent checks who is online before attempting to assign a follow-up or schedule a live transfer. This avoids blind assignments by routing tasks only to active agents. You feed these live team metrics straight into your decision-making chains for smart, real-time workload distribution.

Setup guide

Set up Aircall 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 Aircall 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({
    "aircall-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 Aircall 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 Aircall. 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 Aircall 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 Aircall MCP in LangChain

You install langchain-mcp-adapters and use the MultiServerMCPClient to connect to the server. Call client.get_tools() to fetch tools like list_calls and pass them directly into your agent constructor.

Yes, every execution of get_call_details or list_contacts is tracked inside LangSmith. You get full visibility into token usage, latency, and exact payloads for every phone system action.

Your agent uses ReAct loops to search for a contact with search_contacts and then immediately pulls their call history using list_calls in a single execution chain.

Yes, you can mix these phone tools with database or CRM integrations in the same agent config. Your agent queries customer records and updates call logs in one unified run.

Your call technical details and customer phone numbers never persist on our platform. The MCP Server runs in a sandboxed V8 isolate, passing sensitive communication logs directly to your local runtime.

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