How to Use the Callpicker MCP in LlamaIndex

Q: analyzing call attribution with Callpicker and LlamaIndex?

Yes. Set up a process to run getcalldetails for new calls and index the marketing source and campaign info. Then you can ask your RAG app questions like, “How many calls did we get from Facebook last month?” and get a factual answer.

Build a LlamaIndex RAG system on your call data. Ask about your phone leads and get answers based on facts, not just embeddings.

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 LlamaIndex

Create your Vinkius account to connect Callpicker to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Entire Call History

This MCP Server lets your LlamaIndex app pull call data directly into a knowledge base. You can have it run `list_call_logs` on a schedule, and the results—every phone call, timestamp, and duration—get indexed into your vector store for semantic search. Then you can enrich that index. For each new log, a follow-up query with `get_call_details` can add the specific marketing campaign and source number. Your RAG app now has a searchable history of every inbound phone lead, ready for you to query in natural language.

Query Your Live PBX Configuration

Don't just index calls; index your phone system's configuration. Use the `list_pbx_extensions` and `list_virtual_numbers` tools to create a snapshot of your entire setup and load it into your LlamaIndex knowledge base. Now you can ask your agent questions like, “Which extensions are assigned to the sales team?” or “What virtual number is for the Google Ads campaign?” The agent queries the index for answers grounded in data from your live system. It can even use `get_pbx_system_status` to confirm the system is healthy before responding.

Create Searchable Call Reports

This isn't just for real-time questions. You can build a process that periodically calls `get_cdr_report` and indexes the summary data. Your LlamaIndex application builds a long-term, searchable archive of call performance over months or years. You do the same thing with `list_call_recordings`. Index the metadata about each recording—who called, when, and how long they talked. When a user asks for a specific conversation, your agent finds the metadata in the index and then uses `get_recording_url` to fetch the audio on demand.

Setup guide

Set up Callpicker MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Callpicker MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Callpicker tools.",
)
response = await agent.run("List recent Callpicker data")

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 LlamaIndex

You use the Callpicker tools to fetch live call data from your phone system. Then, you index that data into a vector store. Your LlamaIndex RAG application queries that index to answer questions about your call history and performance.

You index the recording metadata, not the audio itself. Use `list_call_recordings` to get a list, index that list, and then your agent can use `get_recording_url` to retrieve the actual audio file when a user's query requires it.

Yes. Set up a process to run `get_call_details` for new calls and index the marketing source and campaign info. Then you can ask your RAG app questions like, “How many calls did we get from Facebook last month?” and get a factual answer.

No. The Vinkius-managed server is ephemeral and stateless. Your LlamaIndex agent fetches the data, and you control where it's indexed and stored. The MCP server itself holds no long-term data.

The server interacts with your phone system's call metadata, including phone numbers, call durations, and associated marketing sources. Vinkius infrastructure doesn't retain this data; it's passed directly to your LlamaIndex agent over a secure, encrypted connection.

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