How to Use the Callpicker MCP in LangChain

Q: How do I build marketing attribution with Callpicker and LangChain?

Set up an agent that regularly runs getcdrreport. Have it process the data to see which of your virtual numbers gets the most calls, then use getcalldetails to link those numbers back to the specific marketing campaigns you're running.

Build LangChain agents that connect marketing spend to actual phone calls. See which campaigns work and which ones are just noise.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Callpicker MCP to LangChain

Create your Vinkius account to connect Callpicker 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 Callpicker with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Investigate Call Performance

Give your agent a simple goal, like figuring out last month's best lead source. It can start by pulling a high-level summary with `get_cdr_report` to see the overall call volume and patterns across your virtual numbers. From there, the chain can get specific. The agent can use the report's output to find a number worth investigating, then run `list_call_logs` to see its recent activity. To close the loop, it passes a specific call ID to `get_call_details` to see the exact marketing source. That's how you build a real attribution model, one step at a time.

Automate Call Operations

You can build a LangChain agent that does more than just read data. The `make_call` tool lets your agent initiate an outbound call, which you could use to automatically verify a new lead or send a pre-recorded alert to a customer. Good automation requires checks and balances. Before making a call, your agent can first use `get_pbx_system_status` to confirm the phone system is online. It can also pull a list of available lines with `list_pbx_extensions` to make sure it's dialing from the correct department. It's a simple, reliable sequence for your agent to follow.

Manage Call Recordings in a Chain

Your LangChain agent can find and process call recordings automatically. It starts by getting a full inventory with `list_call_recordings`, which you can instruct it to filter by date, duration, or phone number. Once the agent identifies the recording it needs, it uses `get_recording_url` to get a temporary download link. The output of this MCP Server tool can then be chained directly into another tool—one that transcribes audio, analyzes sentiment, or archives the file to cold storage. You get the raw access you need to build powerful audio workflows.

Setup guide

Set up Callpicker 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 Callpicker 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({
    "callpicker-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 Callpicker 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 Callpicker. 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 Callpicker 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 Callpicker MCP in LangChain

You get the tools from the MCP client and pass them to your agent constructor. The agent then reads the tool descriptions to figure out which one to call for a given task, like using `get_call_details` when you ask for info on a specific call.

Yes, that's what it's designed for. A common pattern is using `list_call_logs` to find a recent call ID, then passing that ID as input to the `get_call_details` tool in the very next step of the chain.

Set up an agent that regularly runs `get_cdr_report`. Have it process the data to see which of your virtual numbers gets the most calls, then use `get_call_details` to link those numbers back to the specific marketing campaigns you're running.

You get nine tools focused on call analytics and operations. Key tools include `make_call` for initiating calls, `get_cdr_report` for analytics, and `get_recording_url` to access audio files.

The server only handles your call metadata and recording URLs. Your actual call audio, customer phone numbers, and Call Detail Records are processed ephemerally and never stored by Vinkius. Each request runs in an isolated sandbox and is torn down immediately after.

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