How to Use the JustCall MCP in LlamaIndex

Q: Can I index JustCall SMS messages for semantic search?

Yes. Your setup can pull text batches via listmessages and embed them into your vector store. Users can then search for specific phrases or sentiments across all past texts.

Q: How do I restrict which tools the agent can use?

Pass the allowedtools filter when converting the MCP tool spec. You might allow listcontacts for basic lookups but block listrecordings to restrict access to sensitive audio.

Index your JustCall communication history into LlamaIndex to build searchable, knowledge-grounded RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect JustCall MCP to LlamaIndex

Create your Vinkius account to connect JustCall 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 JustCall with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ingest Call Data into LlamaIndex

RAG applications usually rely on static PDFs, but you can change that by indexing live data from `list_calls`. Your agent pulls every recent customer interaction using the endpoints, then indexes those raw conversations into a vector store. You feed actual telephonic history into your knowledge base. Now your team can query the actual context of customer relationships. When an account manager asks about a client's recent complaints, the agent searches the index and retrieves specific timestamps and notes originally sourced from `get_call`. You get answers grounded in real communication data.

Build a JustCall MCP Server Knowledge Base

You can map out your entire outbound operation by indexing the output of `list_campaigns` alongside `list_numbers`. Telemarketing teams generate thousands of data points daily. The LlamaIndex function agent knows exactly which tools to call to refresh its knowledge base when campaign structures change. This setup prevents the AI from hallucinating account details. If someone asks who owns a specific inbound line, the agent runs `list_users` and cross-references the result against the indexed phone number data. The MCP server feeds the exact organizational layout directly into your search pipeline.

Semantic Search for Audio Logs

You can build an index that tracks audio metadata by calling `list_recordings` and `get_contact`. Quality assurance usually means listening to random calls and hoping you find something useful. The system maps recording URLs to specific customer profiles and indexes the associated call notes. You just ask the agent to find conversations where customers mentioned a specific bug. The LlamaIndex application queries the vector database, identifies the matching IDs, and returns the exact recording links. The MCP endpoints turn unstructured audio metadata into highly searchable text.

Setup guide

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

Run pip install llama-index-tools-mcp and set up a BasicMCPClient. Wrap that client in McpToolSpec so your LlamaIndex function agent can access the communication endpoints.

Yes. Your setup can pull text batches via `list_messages` and embed them into your vector store. Users can then search for specific phrases or sentiments across all past texts.

Not by default. You need to configure a refresh job where the agent calls `list_webhooks` or polls the endpoints to fetch new interactions and update the vector store.

Pass the allowed_tools filter when converting the MCP tool spec. You might allow `list_contacts` for basic lookups but block `list_recordings` to restrict access to sensitive audio.

Vinkius manages the server with strict zero-trust principles. When LlamaIndex retrieves names and phone numbers, the data passes through a secure, ephemeral tunnel. No customer records are stored on the Vinkius infrastructure after the request completes.

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