How to Use the Activepieces MCP in OpenAI Agents SDK

Control your Activepieces automation flows and manage app connections right inside your production OpenAI Agents SDK pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Activepieces MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Programmatic Flow Control

`list_flows` lets your OpenAI agents inspect active automations to decide when to trigger or modify them. Your agent scans the workspace, identifies the correct sequence, and edits it on the fly using `apply_flow_operation` without human intervention. This setup keeps your production workflows predictable. If an agent detects a failing step, it triggers a recovery path instantly. You get full visibility through the OpenAI dashboard while your agent handles the heavy lifting behind the scenes.

OpenAI Agents SDK Connection Controls

`upsert_app_connection` handles your external API keys, OAuth2 tokens, and credentials directly within your runtime. Instead of hardcoding credentials or exposing them to raw agent logs, the MCP server acts as a secure intermediary. You can rotate keys or swap connection parameters using `rotate_mcp_token` to maintain tight security boundaries. This keeps your production environment safe while giving your autonomous agents the access they need to run jobs.

Real-time Execution Auditing

`get_flow_run` pulls the exact execution state of any active or completed automation run straight to your agent. When an error occurs, the agent calls `list_flow_runs` to isolate the broken step and debug the issue in real time. Instead of guessing why a webhook failed, your OpenAI agents read the actual payload. The agent can then automatically fix the bad data or notify your team with precise debugging info.

Setup guide

Set up Activepieces 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 Activepieces tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the library via pip and configure the MCP client with your Vinkius endpoint. Pass this server instance into your Agent constructor using the mcp_servers parameter to auto-discover all 32 tools.

Yes. Your agent can build brand new automations from scratch by calling `create_flow` and structuring the steps dynamically. You can also organize these new runs by calling `create_folder` to keep your workspace clean.

The SDK uses built-in guardrails to check every tool call before it runs. If your agent tries to call `delete_flow` with an invalid ID, the MCP Server catches the error and prevents the destructive action.

You can assign different tools to different specialized agents in your pipeline. For example, one agent can focus on monitoring runs with `list_flow_runs` while another handles configuration tasks like `configure_git_repo`.

Your API keys and connection secrets never touch external logging servers. Vinkius runs the server in an isolated sandbox, keeping your credentials encrypted and hidden from the LLM's training data.

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