How to Use the FlowiseAI MCP in OpenAI Agents SDK

Q: How do I connect FlowiseAI to my OpenAI Agents SDK project?

Install the package using pip install openai-agents and initialize MCPServerStreamableHttp with your Vinkius endpoint. Pass this server instance into your Agent constructor using the mcpservers list to auto-discover all 12 FlowiseAI tools.

Q: Can I run multiple FlowiseAI chatflows concurrently in OpenAI Agents SDK?

Yes, the executechatflowprediction tool runs asynchronously within the SDK's runtime. Your agent can trigger multiple visual pipelines simultaneously while the OpenAI dashboard tracks every execution.

Q: How does OpenAI Agents SDK handle tool caching with FlowiseAI?

Set cacheToolsList=True in your server parameters. This prevents the SDK from repeatedly querying the listchatflows tool, which drops latency and speeds up agent response times.

Q: Can my agent inspect visual templates before running them?

Yes, your agent uses listmarketplacetemplates to fetch available visual structures. It can then query getchatflowdetails to read the exact node layout before initiating a run.

Q: How does this MCP Server secure my FlowiseAI credentials?

The server handles listflowisecredentials requests within a secure, isolated V8 sandbox on Vinkius. Your actual third-party API keys and database credentials never pass through the LLM or leave your protected environment.

Run visual FlowiseAI pipelines directly inside your OpenAI Agents SDK production workflows using this secure 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 FlowiseAI MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run visual chatflows from OpenAI Agents SDK

The `execute_chatflow_prediction` tool lets your agent trigger visual LLM pipelines on demand. Instead of hard-coding complex agent handoffs in Python, you build the logic visually in FlowiseAI and let this MCP Server expose it as a single callable tool. Your agent uses `get_chatflow_details` to inspect the flow structure before triggering it. This ensures your production OpenAI Agents SDK system maintains strict control over which visual pipeline runs, matching the exact parameters expected by your backend.

Synchronize production credentials and variables

The `list_flowise_credentials` tool exposes configured API keys and access tokens to your agent safely. Your OpenAI Agents SDK pipeline reads these configurations without exposing raw secrets in your local codebase, keeping your production environment secure. You manage dynamic runtime behavior using `list_flow_variables`. This lets your agent check active system variables before executing a run, ensuring your visual flow behaves exactly as your Python code expects.

Push production data to vector stores

The `upsert_vector_data` tool lets your OpenAI Agents SDK agent write clean data directly into your connected vector databases. You bypass manual chunking and embedding logic by letting the MCP Server handle the heavy lifting through your visual FlowiseAI setup. Your agent can also call `list_marketplace_templates` to discover pre-built RAG configurations on the fly. This speeds up deployment when your production agents need to spin up new knowledge bases without manual code changes.

Setup guide

Set up FlowiseAI 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 FlowiseAI tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package using `pip install openai-agents` and initialize `MCPServerStreamableHttp` with your Vinkius endpoint. Pass this server instance into your Agent constructor using the `mcp_servers` list to auto-discover all 12 FlowiseAI tools.

Yes, the `execute_chatflow_prediction` tool runs asynchronously within the SDK's runtime. Your agent can trigger multiple visual pipelines simultaneously while the OpenAI dashboard tracks every execution.

Set `cacheToolsList=True` in your server parameters. This prevents the SDK from repeatedly querying the `list_chatflows` tool, which drops latency and speeds up agent response times.

Yes, your agent uses `list_marketplace_templates` to fetch available visual structures. It can then query `get_chatflow_details` to read the exact node layout before initiating a run.

The server handles `list_flowise_credentials` requests within a secure, isolated V8 sandbox on Vinkius. Your actual third-party API keys and database credentials never pass through the LLM or leave your protected environment.

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