How to Use the Customerly MCP in LlamaIndex

Q: How can I use LlamaIndex to find all users in Customerly with a specific tag?

You can build a RAG agent that uses the listusers tool and filters the results. For more complex queries, index all user data first, then ask your agent to find users matching the tag.

Q: Can I ask my LlamaIndex app questions about Customerly conversations?

Absolutely. Set up an ingestion pipeline that uses listconversations and getconversation to pull chat data into a vector index. Then you can query it with natural language.

Index your Customerly data with LlamaIndex. Ask questions about your users, leads, and conversations and get answers grounded in real data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Customerly MCP to LlamaIndex

Create your Vinkius account to connect Customerly 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 Customerly with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a Searchable User Database

Use LlamaIndex to call `list_users` and index the results into a vector store. Now you can ask natural language questions like "show me all users with a @company.com email who signed up last month" and get back a structured list. This goes beyond simple filtering. LlamaIndex lets you query based on the meaning of user attributes. You can find users who are "power users" or "at risk of churning" by indexing their tags and conversation history.

Query Your Conversation History

Don't just list conversations; understand them. Your RAG application can periodically run `list_conversations`, fetch details with `get_conversation`, and index the content. This turns your entire support history into a queryable knowledge base. Ask your agent, "what are the most common feature requests from paying customers?" It will search the indexed conversations, find relevant messages, and synthesize an answer based on actual customer interactions from this MCP Server.

Ground Your LlamaIndex Agent in Live Data

Your agent's knowledge won't go stale. LlamaIndex can be configured to refresh its index by calling Customerly tools on a schedule. It can use `create_update_lead` to add a new lead and immediately index that lead's data for future queries. This creates a feedback loop. Your agent can query the index for context, act on it by calling a tool like `add_tag`, and the result of that action updates the index. The agent learns from its own actions.

Setup guide

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

You can build a RAG agent that uses the `list_users` tool and filters the results. For more complex queries, index all user data first, then ask your agent to find users matching the tag.

Absolutely. Set up an ingestion pipeline that uses `list_conversations` and `get_conversation` to pull chat data into a vector index. Then you can query it with natural language.

Your agent can first query its index to find the right user, then use the `create_update_user` tool to push changes. For example, "find the user with email 'test@test.com' and add the attribute 'plan: premium'."

Yes, LlamaIndex has connectors for most popular vector stores. You can index your Customerly data into the same database you use for your other documents, creating a unified knowledge source.

The data is pulled by your LlamaIndex agent through the secure Vinkius MCP Server endpoint. You control where it's indexed—in your own vector database or a managed one. Vinkius itself doesn't retain any of your lead or conversation content.

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