How to Use the Clientjoy MCP in LlamaIndex

Q: How does indexing work with Clientjoy and LlamaIndex?

LlamaIndex calls the Clientjoy tools, like listcustomers, and takes the JSON output. It then processes and stores this data in a vector index. This allows your agent to perform fast, semantic searches over your CRM data later on.

Turn your Clientjoy sales data into a searchable knowledge base with LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clientjoy MCP to LlamaIndex

Create your Vinkius account to connect Clientjoy 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 Clientjoy with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Entire Client History

This server lets you feed your live CRM data directly into a LlamaIndex vector store. Use tools like `list_customers` and `list_billing_invoices` to pull your complete client and payment history. LlamaIndex then indexes this information, making it instantly searchable. Now you can ask questions in plain English, like "show me all invoices for Acme Corp from last quarter." Your agent finds the answer by searching the indexed data from Clientjoy, not by making repeated API calls. It's a faster, more efficient way to query your own business information through this MCP server.

Build a RAG Pipeline on Your Sales Data

Go beyond simple tool calls by building a Retrieval-Augmented Generation (RAG) application. Use `list_sales_proposals` and `list_service_items` to create a knowledge base of what you sell and who you've sold it to. Your agent can then use this context to generate informed answers. When you ask, "what was our most popular service item last year?" the agent retrieves the relevant data from your indexed proposals and items to answer accurately. It grounds the agent's responses in your actual sales history, preventing it from making things up.

Ground Your LlamaIndex Agent in Real CRM Data

Connecting this server gives your LlamaIndex agent a direct line to reality. Instead of relying only on static documents, your agent can query live data from your CRM. This keeps your knowledge base up-to-date with the latest customer information and sales activities. The `McpToolSpec` makes setup easy. Point it to your Vinkius endpoint, and it converts all seven Clientjoy tools for your agent to use. You can filter which tools the agent has access to, giving you precise control over its capabilities.

Setup guide

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

LlamaIndex calls the Clientjoy tools, like `list_customers`, and takes the JSON output. It then processes and stores this data in a vector index. This allows your agent to perform fast, semantic searches over your CRM data later on.

A RAG pipeline retrieves relevant information before generating an answer. With this MCP server, your LlamaIndex agent can retrieve customer history from your indexed Clientjoy data to provide contextually-aware answers about your business.

Yes, that's the point of using LlamaIndex. Once data from tools like `list_sales_proposals` is indexed, you can ask your agent questions about it indefinitely without having to call the API again for the same information.

Absolutely. The tools from the Clientjoy server can be used alongside any other LlamaIndex data loader or tool. You can build a single agent that queries your CRM, a local database, and a PDF document all at once.

Yes. Your data is protected. The MCP connection itself is encrypted. When LlamaIndex pulls your customer, lead, and proposal data, it's processed within your own environment. Vinkius provides a secure pipe but never inspects or retains your CRM information.

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