How to Use the Activepieces MCP in AutoGen

Q: How do I load Activepieces tools into AutoGen?

Run pip install -U "autogen-extmcp". Use mcpservertools with a StreamableHttpServerParams pointing to your Vinkius endpoint, then pass the tools directly into your AssistantAgent constructor.

Q: Can multiple AutoGen agents use the Activepieces tools simultaneously?

Yes. The McpToolAdapter handles schema conversion so any agent in your chat can call getflow or updateproject. You just need to provide the tool list to the specific agents that need it.

Q: How do agents handle errors when creating a flow?

If createflow returns an error, the executing agent sees the failure message. It will discuss the error with the other agents in the group chat, adjust the parameters, and try the call again.

Q: Is my Activepieces workspace data protected during agent debates?

Yes. When your security agent runs listprojectmembers, the user emails and IDs route through our V8 Isolate Sandbox. Vinkius requires only one endpoint token, and the temporary execution environment vanishes after the data returns to your local machine.

Build multi-agent systems where specialized AutoGen agents debate and manage your Activepieces infrastructure.

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 AutoGen

Create your Vinkius account to connect Activepieces to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Activepieces MCP Server Deployment

You do not want a single agent pushing changes to production workflows. Set up a creator agent that drafts a new sequence and proposes it via `create_flow`. A separate reviewer agent inspects the logic, checking for missing steps or infinite loops. They debate the implementation. If the reviewer finds a flaw, it tells the creator to fix it using `apply_flow_operation`. Only when both agents reach an agreement does a release manager agent trigger `create_project_release` to deploy the update.

Debating Workspace Permissions

Managing who gets access to which project usually requires manual ticket reviews. In AutoGen, an HR agent connects to the MCP Server, receives an onboarding request, and suggests adding the user. A security agent checks the user's role and calls `list_project_members` to verify current group sizes. The security agent might push back if the project is restricted. Once they negotiate the correct permission level, the system executes `invite_user` to finalize the onboarding. The entire access control decision is documented in the agent chat history.

Autonomous Credential Auditing

Stale credentials create security risks that require constant auditing. You can deploy an auditor agent that runs `list_app_connections` and `list_global_connections` to inventory every integration. It flags anything older than ninety days. An operations agent reviews the flagged list and argues for keeping certain connections alive based on recent usage pulled from `list_flow_runs`. When they agree a connection is dead, the ops agent fires `delete_app_connection` to remove it permanently.

Setup guide

Set up Activepieces MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Activepieces tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Activepieces_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Activepieces data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Activepieces_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Activepieces data")
    print(result.messages[-1].content)

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 AutoGen

Run `pip install -U "autogen-ext[mcp]"`. Use `mcp_server_tools` with a `StreamableHttpServerParams` pointing to your Vinkius endpoint, then pass the tools directly into your AssistantAgent constructor.

Yes. The `McpToolAdapter` handles schema conversion so any agent in your chat can call `get_flow` or `update_project`. You just need to provide the tool list to the specific agents that need it.

If `create_flow` returns an error, the executing agent sees the failure message. It will discuss the error with the other agents in the group chat, adjust the parameters, and try the call again.

The framework supports Streamable HTTP transports natively. Your agents can execute long-running operations like `list_flow_runs` without blocking the conversation.

Yes. When your security agent runs `list_project_members`, the user emails and IDs route through our V8 Isolate Sandbox. Vinkius requires only one endpoint token, and the temporary execution environment vanishes after the data returns to your local machine.

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