How to Use the Placetel MCP in LlamaIndex

Q: How do I index Placetel call logs into a LlamaIndex vector store?

You run listcalldetailrecords through the MCP client to fetch the raw logs. The framework then parses this JSON payload into document nodes and embeds them directly into your vector database.

Q: Can LlamaIndex search through Placetel SIP user details?

Yes, your agent can query SIP configurations. By running getsipuser, the agent pulls specific account details and indexes them so they can be retrieved during a natural language query.

Q: Does the Placetel integration support real-time data updates in LlamaIndex?

Yes, you can configure your agent to call listcalls dynamically during a query. This ensures the agent's answers are based on active phone sessions rather than stale, cached indices.

Q: What tools should I include for a basic VoIP search agent?

You should register listusers, listdevices, and listnumbers when setting up the MCP tool spec. This gives your agent enough context to resolve most employee hardware and phone number queries.

Index Placetel call logs and SIP configurations directly into LlamaIndex vector stores for semantic search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Placetel MCP to LlamaIndex

Create your Vinkius account to connect Placetel to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Placetel with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Placetel numbers in LlamaIndex

The `list_numbers` tool retrieves your company's entire phone inventory so your LlamaIndex MCP agent can index it for semantic search. Instead of manually searching through spreadsheets, your agent queries this live index to find which departments own specific virtual lines. The framework stores these numbers alongside metadata, allowing your RAG pipeline to ground its answers in real-time telecom data. This prevents the model from hallucinating routing paths or inventing phone assignments.

Ground RAG queries in actual call logs

The `list_call_detail_records` tool pulls raw telecom data that your LlamaIndex pipeline converts into searchable document nodes. Your agent parses these nodes to answer questions about call volumes, peak hours, and average talk times. By linking live telecom records to your vector store, you build a self-updating knowledge base. The agent uses `list_calls` to fetch current activity and merges it with historical records for immediate analysis.

Search SIP configurations with an MCP Server

The `list_sip_users` tool extracts active SIP credentials and device associations into your index. Your LlamaIndex agent uses this data to map out your infrastructure, matching users with their physical hardware via `list_devices`. This mapping turns raw API responses into a structured knowledge graph. You can query the agent about system health, and it will pull the exact status of your VoIP setup without needing manual API calls.

Setup guide

Set up Placetel 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 Placetel 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 Placetel tools.",
)
response = await agent.run("List recent Placetel 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 Placetel. 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 Placetel 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 Placetel MCP in LlamaIndex

You run `list_call_detail_records` through the MCP client to fetch the raw logs. The framework then parses this JSON payload into document nodes and embeds them directly into your vector database.

Yes, your agent can query SIP configurations. By running `get_sip_user`, the agent pulls specific account details and indexes them so they can be retrieved during a natural language query.

Yes, you can configure your agent to call `list_calls` dynamically during a query. This ensures the agent's answers are based on active phone sessions rather than stale, cached indices.

You should register `list_users`, `list_devices`, and `list_numbers` when setting up the MCP tool spec. This gives your agent enough context to resolve most employee hardware and phone number queries.

Your SIP credentials, phone numbers, and call logs are processed in a zero-trust, ephemeral sandbox. Vinkius never caches this telecom data, keeping it strictly between your local vector index and the Placetel API.

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