How to Use the CHATFLY MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK read my CHATFLY customer conversations?

Yes. The agent calls listflyconversations to find recent threads. It then uses getconversationhistory to pull the specific messages into its context.

Build production customer support agents with OpenAI Agents SDK that manage your CHATFLY bots and track conversation histories.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CHATFLY MCP to OpenAI Agents SDK

Create your Vinkius account to connect CHATFLY to OpenAI Agents SDK 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 CHATFLY with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

OpenAI Agents SDK routing for bots

Managing specialized support bots requires strict routing handoffs in production systems. Your primary OpenAI agent can inspect incoming customer queries, then use `list_chatfly_bots` to find the specific bot trained for that product line. It grabs the exact configuration using `get_chatbot_details` before deciding how to proceed. You do not want agents guessing at context. By calling `get_conversation_history`, the routing agent pulls the entire previous thread into its context window. It then passes that exact state to a specialized worker agent, ensuring the customer never repeats themselves.

Safe knowledge base updates

Guardrails keep your support infrastructure and knowledge base from breaking. Before your agent touches the training data, it checks your quota via `get_chatfly_account_info`. If you have enough resources, it reviews the current files with `list_uploaded_documents`. Training a model takes time and compute. You can configure OpenAI guardrails to require human approval before the agent executes `trigger_bot_training`. Once approved, the agent fires the training job and logs the entire trace in your OpenAI dashboard.

Active testing with live messaging

Deploying untested support flows ruins customer trust, requiring active bot testing. Your evaluation agent can spin up, pull recent interactions using `list_fly_conversations`, and extract the hardest questions your human reps faced yesterday. The agent then fires those exact questions back at your staging bot using `send_bot_message`. Because this MCP Server runs through Vinkius, the connection stays secure while you validate the bot's responses against your strict production criteria.

Setup guide

Set up CHATFLY MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all CHATFLY tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives CHATFLY tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate CHATFLY tools and returns structured results. Copy the full example on the right to get started.

agent.py

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

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="CHATFLY Agent",
            instructions="You have access to CHATFLY tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 CHATFLY. 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 CHATFLY 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 CHATFLY MCP in OpenAI Agents SDK

Install the openai-agents package via pip. Create an MCPServerStreamableHttp instance pointing to your Vinkius endpoint, then pass it to your Agent constructor inside an async context manager.

Yes. The agent calls `list_fly_conversations` to find recent threads. It then uses `get_conversation_history` to pull the specific messages into its context.

Tools auto-discover instantly. You skip writing custom API wrappers and authentication logic, letting your agent immediately start managing chatbots and triggering training runs.

Set cacheToolsList=True in your MCP configuration. This prevents the agent from fetching the tool schema on every single turn.

This integration touches raw customer support messages and knowledge base documents. The V8 Isolate Sandbox destroys the execution environment the millisecond the request finishes, leaving zero traces of your chat history behind.

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