How to Use the Flow XO MCP in LlamaIndex

Q: How does the Flow XO MCP Server integrate with LlamaIndex vector stores?

You load the tool outputs from listchatbotusers or listworkflows as document objects, then pass them to your vector index. This makes your live chatbot user lists and workflow structures semantic-searchable by your query engine.

Q: Does LlamaIndex support filtering which Flow XO tools are exposed?

Yes, you can use the allowedtools filter during initialization to restrict your agent's access. For instance, you can expose only getautomationanalytics while blocking destructive tools like toggleworkflow.

Q: How is my Flow XO user profile data protected in LlamaIndex?

Your user profiles, accessed via getuserdetails and listchatbotusers, are processed in-memory within your secure LlamaIndex runtime. The Vinkius MCP Server platform executes these requests inside zero-trust, ephemeral V8 isolates, meaning no customer metadata is cached or stored externally.

Index Flow XO user analytics and automate chatbot workflows directly from your LlamaIndex RAG pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flow XO MCP to LlamaIndex

Create your Vinkius account to connect Flow XO 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 Flow XO with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Bot Configurations in LlamaIndex

The `list_bot_accounts` tool gets your active platform accounts so LlamaIndex can index them as document nodes. This allows your query engine to retrieve live bot configurations when answering administrative questions. Your pipeline parses the structural data from this MCP Server and converts it into searchable vector embeddings. When a user asks which automations are active, the agent retrieves the relevant nodes and uses `toggle_workflow` if changes are requested.

Grounded Analytics Search

The `get_automation_analytics` tool feeds live usage summaries directly into your RAG retrieval context. Instead of guessing performance trends, your agent queries this tool to get real-time metrics. The engine combines these analytics with historical logs from `list_broadcasts` to generate performance reports. This guarantees that your agent's insights are grounded in actual Flow XO data, eliminating hallucinated statistics.

Semantic Querying of User History

The `list_user_history` tool pulls message logs so your LlamaIndex agent can perform semantic searches over past interactions. This lets you find specific customer complaints or feature requests buried in chat logs. When the agent identifies an issue, it uses `update_user` to tag the profile or `send_push_message` to send a direct follow-up. This turns raw conversational logs into structured, actionable knowledge.

Setup guide

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

You load the tool outputs from `list_chatbot_users` or `list_workflows` as document objects, then pass them to your vector index. This makes your live chatbot user lists and workflow structures semantic-searchable by your query engine.

Yes, your query engine can resolve natural language questions about users by calling `get_user_details` under the hood. The tool supplies the raw profile data, which LlamaIndex formats into a natural response.

You initialize the BasicMCPClient with the Vinkius endpoint, convert it using McpToolSpec, and call the asynchronous tool listing method. This registers tools like `trigger_webhook` and `send_push_message` directly with your LlamaIndex FunctionAgent.

Yes, you can use the allowed_tools filter during initialization to restrict your agent's access. For instance, you can expose only `get_automation_analytics` while blocking destructive tools like `toggle_workflow`.

Your user profiles, accessed via `get_user_details` and `list_chatbot_users`, are processed in-memory within your secure LlamaIndex runtime. The Vinkius MCP Server platform executes these requests inside zero-trust, ephemeral V8 isolates, meaning no customer metadata is cached or stored externally.

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