How to Use the SmartChatAI MCP in LlamaIndex

Q: Can I query past bot activity using SmartChatAI in LlamaIndex?

Yes. You use getbotchathistory to retrieve transcripts, and LlamaIndex then indexes them so you can perform semantic searches on old conversations.

Q: What data does SmartChatAI touch when managing bots in LlamaIndex?

It manages bot configurations (getchatbotdetails) and stores conversation transcripts, which are the core pieces of data that LlamaIndex indexes for semantic retrieval.

RAG applications built with LlamaIndex powered by the SmartChatAI MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect SmartChatAI MCP to LlamaIndex

Create your Vinkius account to connect SmartChatAI to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup SmartChatAI with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Indexing Live Conversations

LlamaIndex excels at turning data into search vectors. Use `get_bot_chat_history` to pull conversation transcripts, and LlamaIndex indexes that raw text into a semantic store. You can then query past sessions—not just the latest chat—and get answers grounded in actual API dialogue. This capability turns transient message logs into permanent, searchable knowledge. Your RAG application bypasses hallucinations by retrieving context directly from indexed conversation data.

Multi-Format Knowledge Ingestion

You can train your index on three sources: raw text using `add_text_to_knowledge_base`, an entire website via `add_website_to_knowledge_base`, or complex PDFs with `add_pdf_to_knowledge_base`. Each method feeds a unique, searchable data chunk into the unified vector store. This allows your LlamaIndex agent to synthesize answers from heterogeneous sources—a user manual (PDF) combined with current policy rules (website)—all in one query.

API Data Grounding

Don't just rely on general knowledge. When you call `get_chatbot_details` or `list_ai_chatbots`, LlamaIndex captures that structural API data and indexes it. Users can then ask questions like, 'What is the configuration for Bot X?' and get a precise answer pulled from the stored metadata. This provides immediate validation of system state, making your application far more trustworthy than general-purpose chatbots.

Setup guide

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

The MCP Server exposes functions that LlamaIndex can call and index. For example, calling `message_ai_chatbot` provides the live data LlamaIndex uses to build its searchable knowledge base.

Yes. You use `get_bot_chat_history` to retrieve transcripts, and LlamaIndex then indexes them so you can perform semantic searches on old conversations.

It manages bot configurations (`get_chatbot_details`) and stores conversation transcripts, which are the core pieces of data that LlamaIndex indexes for semantic retrieval.

You feed the tools to your FunctionAgent. The key is recognizing that every tool call, like `list_ai_chatbots`, provides a data payload that LlamaIndex can treat as source material.

It processes and stores structured documents (PDFs, text) and indexed URLs/web pages. This allows the system to retrieve answers based on verifiable source material.

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