How to Use the Aircall MCP in LlamaIndex

Q: Can I index Aircall contact lists into a vector store?

Yes, you can retrieve contact records using listcontacts and load them into a LlamaIndex document store. This lets you perform semantic vector search over your customer phone directory.

Q: Does LlamaIndex support real-time Aircall team lookups?

Yes, the agent calls getuserdetails dynamically during execution to check availability before making routing decisions based on your indexed data.

Q: How do I filter which phone tools the indexer can access?

You use the allowedtools filter when setting up your tool specification. This limits your agent's scope to specific tools like listnumbers while blocking write operations.

Index Aircall phone logs and contact lists directly into your LlamaIndex vector stores for ground-truth RAG.

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 LlamaIndex

Create your Vinkius account to connect Aircall 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 Aircall with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Live Call Logs for LlamaIndex RAG

The `list_calls` and `get_call_details` tools pull historical call data and technical metrics directly into your LlamaIndex pipelines. Your system indexes these call logs into a vector store to make your customer interaction history fully searchable. This MCP connection prevents your agent from hallucinating customer history. It queries the actual indexed call records to ground its answers in verified communication data.

Ground Agent Answers with Aircall Contact Indexes

The `list_contacts` and `search_contacts` tools allow your LlamaIndex agent to query and index your entire customer directory. Your agent matches incoming phone queries against this index to retrieve precise customer profiles. By feeding this contact data into your vector database, you build a RAG system that knows exactly who is calling. Your queries return real, structured contact records rather than guessed details.

Map Team Capabilities via LlamaIndex MCP Server Queries

The `list_teams` and `list_users` tools expose your organization's structure and active agents to your LlamaIndex queries. Your search pipeline queries this index to find the best-suited team member for a specific customer issue. This makes your internal directory searchable alongside customer files. Your agent matches the context of a support ticket to the skills of active teams retrieved from the live directory.

Setup guide

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

Install llama-index-tools-mcp and initialize the BasicMCPClient. Convert the server tools using McpToolSpec and pass them to your FunctionAgent to start querying phone data.

Yes, you can retrieve contact records using list_contacts and load them into a LlamaIndex document store. This lets you perform semantic vector search over your customer phone directory.

Yes, the agent calls get_user_details dynamically during execution to check availability before making routing decisions based on your indexed data.

You use the allowed_tools filter when setting up your tool specification. This limits your agent's scope to specific tools like list_numbers while blocking write operations.

All retrieved contact phone numbers and names are processed in memory within secure, ephemeral V8 environments. This MCP Server ensures your customer records are never stored or cached on our infrastructure.

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