How do I trigger a specific Flow XO workflow using the agent?

You can use the 'trigger_webhook' tool. Provide the Webhook URL generated by your Flow XO 'Webhook Trigger' and a JSON payload. The agent will post the data to that URL, starting the automated flow remotely.

What is a 'response path' and how do I get it?

A response path is a unique identifier for a user's conversation on a specific platform. You can find it by using the 'list_chatbot_users' or 'get_user_details' tools. It's required for sending push messages via the 'send_push_message' tool.

Can I disable a chatbot flow temporarily using the agent?

Yes! The 'toggle_workflow' tool allows you to enable or disable any of your flows by providing the Workflow ID and setting the 'active' parameter to true or false.

Flow XO MCP Server for OpenAI Agents SDK 12 tools — connect in under 2 minutes

Name: Flow XO
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 12 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Flow XO through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Flow XO Assistant",
            instructions=(
                "You help users interact with Flow XO. "
                "You have access to 12 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Flow XO"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Flow XO MCP Server

Connect your Flow XO account to any AI agent and automate your chatbot interactions and messaging workflows through the Model Context Protocol (MCP). Flow XO is a versatile platform for building and managing chatbots across various channels like Slack, Telegram, and the web. Now, you can manage your automation flows, oversee chatbot users, and trigger webhook-based workflows directly through natural conversation.

The OpenAI Agents SDK auto-discovers all 12 tools from Flow XO through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Flow XO, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Workflow Management — List all your chatbot flows and toggle their active status (enable/disable) instantly.
User Oversight — Access your end-user database, fetch detailed profiles, and create or update user records.
Direct Messaging — Send push messages directly to users via their unique response paths from your chat interface.
Webhook Triggers — Push data payloads to Flow XO webhook trigger URLs to start automated sequences remotely.
Interaction History — Retrieve the message history for specific users to understand past bot engagements.
Platform Connectivity — List all connected bot accounts and platforms (Slack, Messenger, etc.) for better integration context.
Automation Analytics — Fetch high-level usage summaries and performance metrics for your chatbot environment.

The Flow XO MCP Server exposes 12 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Flow XO to OpenAI Agents SDK via MCP

Follow these steps to integrate the Flow XO MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 12 tools from Flow XO

Why Use OpenAI Agents SDK with the Flow XO MCP Server

OpenAI Agents SDK provides unique advantages when paired with Flow XO through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Flow XO + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Flow XO MCP Server delivers measurable value.

Automated workflows: build agents that query Flow XO, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries Flow XO, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Flow XO tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Flow XO to resolve tickets, look up records, and update statuses without human intervention

Flow XO MCP Tools for OpenAI Agents SDK (12)

These 12 tools become available when you connect Flow XO to OpenAI Agents SDK via MCP:

create_user

get_automation_analytics

Get usage summary

get_user_details

Get user profile

list_bot_accounts

). List platform accounts

list_broadcasts

List sent broadcasts

list_chatbot_users

List all end users

list_user_history

List user messages

list_workflows

List automation flows

send_push_message

Send a push message

toggle_workflow

Enable/Disable a flow

trigger_webhook

Trigger flow via webhook

update_user

Update user metadata

Example Prompts for Flow XO in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Flow XO immediately.

"List all my Flow XO chatbot users."

"Disable the workflow 'Old Customer Survey'."

"Send a push message to path 'abc/123': 'Your order has been shipped!'."

Troubleshooting Flow XO MCP Server with OpenAI Agents SDK

Common issues when connecting Flow XO to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Flow XO + OpenAI Agents SDK FAQ

Common questions about integrating Flow XO MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.