How to Use the Landbot MCP in LlamaIndex

Q: How do I filter which Landbot tools LlamaIndex can use?

Pass the allowedtools parameter during setup. This restricts your RAG application to safe read-only operations like fetching chat logs if you want to prevent automated replies.

Index live conversational data and build grounded RAG applications with the Landbot MCP Server and LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Landbot MCP to LlamaIndex

Create your Vinkius account to connect Landbot 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 Landbot with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index active bot configurations

The `list_bots` and `get_bot` tools pull active routing definitions directly into your LlamaIndex vector store. Your system reads exactly how current flows are structured. This prevents the agent from hallucinating capabilities that do not exist in your actual setup. You query this indexed data to troubleshoot customer journeys. If a user gets stuck, the agent cross-references the live bot configuration with your internal documentation to find the exact node causing friction.

Ground answers in real chat history

The `get_messages` operation feeds actual customer chat sequences into your LlamaIndex knowledge base. You extract the exact back-and-forth dialogue for a specific user ID. The agent uses this historical context to generate accurate summaries or suggest next steps. Instead of relying on generic support scripts, your RAG pipeline searches recent interactions via the MCP integration. You run `list_customers` to build an index of active users, then analyze their specific pain points using real conversational data.

Execute actions from the MCP Server

Your FunctionAgent triggers `send_text_message` immediately after finding the right answer in your document index. It searches your knowledge base, constructs the reply, and pushes it to the user. The system turns static retrieval into an active communication channel. You handle escalations the same way. When semantic search fails to find a high-confidence answer, the agent calls `assign_agent` to route the session to a human.

Setup guide

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

Install llama-index-tools-mcp first. Initialize BasicMCPClient with your endpoint, then use McpToolSpec to convert the operations for your FunctionAgent.

You handle that via the search operations. The agent calls search_customers by email, retrieves the metadata via get_customer, and embeds that context into your vector store.

Yes, your agent actively responds. After querying your index for the correct information, it executes the text dispatch tool to reply in the active chat.

Pass the allowed_tools parameter during setup. This restricts your RAG application to safe read-only operations like fetching chat logs if you want to prevent automated replies.

Every connection runs in an ephemeral zero-trust environment. When your indexer retrieves metadata via get_customer, the server processes the request and instantly destroys the container. Your API tokens never persist on disk.

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