How to Use the Voiceflow MCP in OpenAI Agents SDK

Q: How do I search for knowledge using Voiceflow and the OpenAI Agents SDK?

You call querykb to ask a specific question against your content. The agent then retrieves relevant information, ensuring its responses are accurate and grounded in your defined knowledge base.

Q: Can I check session variables with Voiceflow and the OpenAI Agents SDK?

Yes. Your AI client uses getstate to pull the current user context or variable values at any point during the conversation flow. This is critical for complex, stateful interactions.

Q: Does Voiceflow support transcript history with the OpenAI Agents SDK?

Absolutely. The listtranscripts tool lets you pull a list of previous chat sessions. From there, your agent can fetch details using gettranscript, providing full historical context for analysis.

Build production AI agents with the OpenAI Agents SDK and Voiceflow MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Voiceflow MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Session Context

The agent maintains conversation context by checking user variables using `get_state`. It can then update or reset that information when needed, either via `save_state` or a complete session wipe with `delete_state`. This ensures your deployed product handles complex multi-turn conversations correctly. You’re not building a prototype; you're setting up an agent that reliably tracks user intent throughout the interaction.

Query Knowledge Bases

Agents find answers by listing available documentation with `list_kb_docs` and then running targeted searches using `query_kb`. This keeps the conversation grounded in accurate, up-to-date company information. Need to know what kind of data is searchable? You can check the document categories first by calling `list_kb_tags`, giving your agent full visibility into its knowledge source.

Control Conversation Flow

The agent sends messages back to Voiceflow using the `interact` tool, driving the conversation forward. It also gets a detailed record of what was said via `get_transcript`. If you need to audit performance or review past chats, your AI client can list previous interactions with `list_transcripts`, giving you full oversight on user engagement.

Setup guide

Set up Voiceflow 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 Voiceflow tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Voiceflow 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="Voiceflow Agent",
            instructions="You have access to Voiceflow 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 Voiceflow. 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 Voiceflow 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 Voiceflow MCP in OpenAI Agents SDK

You call `query_kb` to ask a specific question against your content. The agent then retrieves relevant information, ensuring its responses are accurate and grounded in your defined knowledge base.

Yes. Your AI client uses `get_state` to pull the current user context or variable values at any point during the conversation flow. This is critical for complex, stateful interactions.

Absolutely. The `list_transcripts` tool lets you pull a list of previous chat sessions. From there, your agent can fetch details using `get_transcript`, providing full historical context for analysis.

It's built for deployment. The server supports robust state management, ensuring that even complex dialog flows don't lose track of where they are in the conversation.

This server touches user conversation state variables. This includes session context, project details (`get_project`), and conversational flow parameters that define where the user is in the dialogue.

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