How to Use the Customers.ai MCP in LlamaIndex

Q: Can LlamaIndex update Customers.ai contacts during a query?

Yes, the agent can call updatecontactattributes or addtagtocontact mid-query if it detects new user preferences during the conversation.

Q: How does the Customers.ai MCP Server handle large lists of leads in LlamaIndex?

The listxrayleads tool returns paginated arrays of identified visitors. LlamaIndex processes these batches sequentially, embedding them into your vector store without hitting memory limits.

Q: Can I query past outreach sessions with LlamaIndex?

You can index the results of getcontact and past messages to build a queryable history. This ensures your agent knows exactly what was sent to a contact before sending another message.

Index identified website leads and contact data directly into your LlamaIndex vector stores for semantic search and RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Customers.ai MCP to LlamaIndex

Create your Vinkius account to connect Customers.ai 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 Customers.ai with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic search over identified website visitors

`list_xray_leads` extracts live visitor identities so LlamaIndex can index them for semantic querying. Instead of running database queries, you query your index for 'visitors from tech companies' and let the engine retrieve the correct profiles. This setup turns raw API responses into searchable documents. The framework takes the structured data from the MCP Server and embeds it directly into your vector database of choice.

Grounding agent responses in real-time contact profiles

`get_contact` pulls the latest profile details to ground your LlamaIndex agent's responses in actual user data. By querying the index, the agent pulls the profile and drafts a personalized email without hallucinating contact details. You avoid outdated context by fetching fresh data through the live API. If the agent needs to update a record, it calls `update_contact_attributes` to keep your system of record accurate.

RAG-driven outreach personalization with LlamaIndex MCP Server

`send_rich_message` sends structured JSON offers to contacts based on knowledge retrieved from your LlamaIndex vector store. After matching a contact's browsing history with your product documentation, the agent sends a highly targeted message. You can also use `add_tag_to_contact` to mark which documents or products the visitor showed interest in. This builds a rich history of interactions that informs future automated chats.

Setup guide

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

You load the tools using the MCP tool spec and run them to fetch contact data. The output is converted into document objects, which you then ingest into your vector index for semantic search.

Yes, the agent can call `update_contact_attributes` or `add_tag_to_contact` mid-query if it detects new user preferences during the conversation.

The `list_xray_leads` tool returns paginated arrays of identified visitors. LlamaIndex processes these batches sequentially, embedding them into your vector store without hitting memory limits.

You can index the results of `get_contact` and past messages to build a queryable history. This ensures your agent knows exactly what was sent to a contact before sending another message.

Data fetched via the MCP Server is processed in transit using secure V8 isolates. Your API keys are encrypted at rest, and we never store the contact profiles or visitor names that pass through the proxy.

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