How to Use the Flodesk MCP in OpenAI Agents SDK

Q: How do I configure the Flodesk MCP Server inside my OpenAI Agents SDK pipeline?

Install the package and use the MCPServerStreamableHttp context manager. You pass this MCP server object directly into your agent constructor to auto-discover all ten tools.

Q: How does the OpenAI Agents SDK trace errors when a Flodesk workflow fails?

Every call to addsubscribertoworkflow appears in your OpenAI developer dashboard. You can inspect the raw payload and see exactly why a transition failed.

Q: How do I fetch custom fields using this integration?

The listcustomfields tool retrieves your account's metadata schema. Your agent reads these fields to map inbound user data to the correct profile properties.

Run production OpenAI Agents SDK systems that safely trigger Flodesk workflows and segment subscribers with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flodesk MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Secure automated segmentation via OpenAI Agents SDK

This MCP Server exposes `create_segment` and `add_subscriber_to_segment` directly to your OpenAI Agents SDK runtime. Your OpenAI Agents SDK assistants inspect incoming lead data, decide which Flodesk list fits best, and execute the classification instantly. No manual sorting needed. Guardrails in the OpenAI Agents SDK intercept these Flodesk calls before execution to prevent accidental bulk updates. You set the rules, and the OpenAI Agents SDK verifies that the agent only touches verified Flodesk subscriber addresses during runtime.

Safe workflow triggers without manual intervention

The `add_subscriber_to_workflow` tool lets your OpenAI Agents SDK assistant drop contacts into automated Flodesk sequences based on their recent interactions. It just works. If a user signs up for a webinar, your OpenAI Agents SDK script handles the registration and kicks off the Flodesk email drip series immediately. The OpenAI Agents SDK traces every single Flodesk workflow trigger directly on your OpenAI dashboard. This visibility means you can audit exactly why an OpenAI Agents SDK assistant chose a specific Flodesk sequence, catching logic loops before they email your users.

Data synchronization with real-time profile updates

The `upsert_subscriber` tool updates Flodesk profiles or creates new records using only an email address inside your OpenAI Agents SDK environment. Your OpenAI Agents SDK assistant queries existing details with `get_subscriber` to determine if a Flodesk record needs custom metadata updates before sending. Running this within the OpenAI Agents SDK means you can manage multi-agent handoffs where one agent extracts custom fields and another writes them to Flodesk. The OpenAI Agents SDK manages these transitions without dropping Flodesk subscriber data or losing the execution context.

Setup guide

Set up Flodesk 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 Flodesk tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package and use the `MCPServerStreamableHttp` context manager. You pass this MCP server object directly into your agent constructor to auto-discover all ten tools.

Yes, because you can apply execution guardrails. The SDK inspects calls to `upsert_subscriber` and blocks them if the batch size exceeds your safety thresholds.

Every call to `add_subscriber_to_workflow` appears in your OpenAI developer dashboard. You can inspect the raw payload and see exactly why a transition failed.

The `list_custom_fields` tool retrieves your account's metadata schema. Your agent reads these fields to map inbound user data to the correct profile properties.

All subscriber emails and segment definitions are isolated within the Vinkius V8 sandbox. No data is stored on our servers, and this MCP connection communicates over a secure, single-tenant encrypted HTTP tunnel.

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