How to Use the ChatGen MCP in LlamaIndex

Q: How does LlamaIndex use the ChatGen MCP Server tools?

You'll use McpToolSpec to wrap the client, which exposes all the ChatGen tools like listbots to your LlamaIndex agent. The agent can then call these tools to fetch data for indexing or to answer a query directly.

Q: Can I filter which ChatGen tools my LlamaIndex agent can use?

Yes. When you initialize the McpToolSpec, you can pass an allowedtools filter. This lets you restrict the agent to only use read-only tools like getbot and listleads, preventing it from accidentally calling deletebot.

Turn ChatGen conversations and bot configurations 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 ChatGen MCP to LlamaIndex

Create your Vinkius account to connect ChatGen 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 ChatGen with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index and Query Your Chatbot Fleet

LlamaIndex can now treat your ChatGen setup as a living document. Use the `list_bots` and `get_bot` tools to ingest the configuration of every chatbot you're running. This data from your MCP Server becomes a queryable index. Now you can ask questions in natural language like, "Which bots are assigned to the marketing team?" or "What's the welcome message for the 'homepage-qualifier' bot?" LlamaIndex searches the indexed data from the `get_bot` tool and gives you a direct answer, grounded in your actual configuration.

Build RAG on Live Lead Data with LlamaIndex

This is where it gets interesting. Your LlamaIndex application can periodically run `list_leads` and `list_conversations`, feeding the results directly into a vector store. You're creating a real-time memory of every customer interaction. With this indexed data, you can build powerful RAG agents. Ask "What are the most common questions from leads in the past 24 hours?" and the agent will synthesize an answer from the indexed `list_conversations` data. This server provides the live data feed for your knowledge base.

Augment Chats with Past Context

Instead of just answering questions, use LlamaIndex to provide context. When a new lead starts a chat, you can query your indexed history of conversations and leads. You might find this person has chatted before or asked similar questions. You can use tools like `get_lead_details` to pull info on an existing lead, and then query your LlamaIndex vector store for related conversations. This gives your agent a massive advantage, letting it respond with full knowledge of the customer's history with your bots.

Setup guide

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

You'll use `McpToolSpec` to wrap the client, which exposes all the ChatGen tools like `list_bots` to your LlamaIndex agent. The agent can then call these tools to fetch data for indexing or to answer a query directly.

Yes, that's a primary use case. You can set up a pipeline that automatically calls `list_leads` and `list_conversations` on a schedule. The text from those conversations is then indexed, making it searchable for your RAG application.

LlamaIndex allows for semantic search. You can ask conceptual questions like "summarize recent chats about pricing" instead of writing a rigid SQL query. It finds relevant information in your `list_conversations` data even if the keywords don't match exactly.

Yes. When you initialize the `McpToolSpec`, you can pass an `allowed_tools` filter. This lets you restrict the agent to only use read-only tools like `get_bot` and `list_leads`, preventing it from accidentally calling `delete_bot`.

When your agent calls a tool, the request for lead details or bot configurations is sent through a dedicated, short-lived Vinkius environment. The data is never logged or stored by Vinkius. You control access, and the connection is encrypted.

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