How to Use the CallPage MCP in LangChain

Q: Can a LangChain agent manage multiple CallPage widgets?

Yes, it can. The agent uses listwidgets to fetch all active widgets on your site. From there, it can inspect specific configurations using getwidgetsettings to adjust routing rules.

Q: How does LangChain handle call recordings from CallPage?

The agent calls listcalls to fetch recent callback records, which include links to the audio files. You can feed these URLs into downstream transcription or analysis chains.

Feed live callback data and lead records directly into your LangChain runs to close deals faster.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CallPage MCP to LangChain

Create your Vinkius account to connect CallPage 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 CallPage with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate callback routing in LangChain

Your agent can instantly pull active leads using `list_leads` and map them to the right team. By calling `list_departments` right after, the model decides where to route the caller without you writing custom glue code. LangChain chains these steps together based on live widget data. If a high-value prospect submits a form, the agent looks up `list_managers` to assign the lead immediately.

Trace CallPage MCP Server actions in LangSmith

Debugging sales workflows is simple when you can see every tool call in your tracing dashboard. When your agent runs `get_call_details` to check why a callback failed, LangSmith logs the exact payload and latency. This setup gives you full visibility into how your model handles customer data. You can spot failing runs or slow API responses when fetching records with `list_calls` before they impact your sales pipeline.

Trigger SMS updates based on call history

Build a chain that acts right after a call ends. The agent pulls the call status with `get_call_details`, checks your templates using `list_sms_templates`, and prepares the follow-up text. You don't have to manually check if a rep spoke with a prospect. The chain inspects the call outcome and selects the correct message template automatically.

Setup guide

Set up CallPage 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 CallPage 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({
    "callpage-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 CallPage 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 CallPage. 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 CallPage 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 CallPage MCP in LangChain

Install the required adapter package first. Then, spin up the multi-server client pointing to your Vinkius endpoint. Pass those tools directly to your agent runner.

Yes, it can. The agent uses `list_widgets` to fetch all active widgets on your site. From there, it can inspect specific configurations using `get_widget_settings` to adjust routing rules.

The agent calls `list_calls` to fetch recent callback records, which include links to the audio files. You can feed these URLs into downstream transcription or analysis chains.

No, Vinkius handles the authentication layer for you. Your agent only needs one secure token to access all ten tools safely.

All lead details and call records stay inside an ephemeral sandbox during execution. Vinkius runs this MCP server in an isolated environment, ensuring your customer phone numbers and contact details are never stored or exposed.

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