How to Use the Relay Workflow Automation MCP in AutoGen

Q: How do AutoGen agents collaborate to trigger Relay Workflow Automation?

One agent uses listworkflows to find the correct pipeline, while another builds the input payload. They debate the parameters before a third agent calls runworkflow.

Q: Can AutoGen automatically cancel a failing Relay Workflow Automation run?

Yes. An agent monitoring the run with getrunstatus can invoke cancelrun if it detects an error or timeout.

Q: What is the setup process for using the Relay Workflow Automation MCP Server with AutoGen?

Install autogen-extmcp and use mcpservertools with StreamableHttpServerParams to fetch the tools. Pass the resulting tool list directly into your AssistantAgent.

Q: How do agents handle schema validation for this MCP Server?

The McpToolAdapter automatically translates the JSON schemas of the tools into the format AutoGen agents expect. This ensures error-free tool calling during conversations.

Coordinate Relay Workflow Automation runs through consensus-driven AutoGen agent conversations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Relay Workflow Automation MCP to AutoGen

Create your Vinkius account to connect Relay Workflow Automation to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Relay Workflow Automation with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Trigger executions via AutoGen agent debate

The `run_workflow` tool executes automated pipelines only after your AutoGen agents agree on the input parameters. A developer agent drafts the payload, a security agent inspects it, and they execute the run over MCP once consensus is reached. This setup prevents accidental or malformed executions. By requiring multi-agent validation before calling the API, you eliminate the risk of passing bad parameters to live systems.

Monitor and manage runs using the MCP Server

The `get_run_status` tool allows your monitoring agent to track active executions and report back to the coordinator agent. If a run fails or hangs, the monitoring agent flags the issue in the conversation thread. Upon detecting a failure, a recovery agent can call `cancel_run` to stop the stuck execution. The agents then discuss the failure reason by analyzing the logs retrieved from `list_runs`.

Discover available workflows through agent dialogue

The `list_workflows` tool lets your discovery agent inspect the available automation pipelines in your Relay account. The agent shares this list in the group chat so other agents know what tools are available. When a task requires a specific automation, the coordinator agent uses `get_workflow` to fetch the precise schema. This ensures the entire conversational group stays aligned on the required input formats.

Setup guide

Set up Relay Workflow Automation 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 Relay Workflow Automation 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="Relay Workflow Automation_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Relay Workflow Automation 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="Relay Workflow Automation_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Relay Workflow Automation 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 Relay. 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 Relay Workflow Automation 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 Relay Workflow Automation MCP in AutoGen

One agent uses `list_workflows` to find the correct pipeline, while another builds the input payload. They debate the parameters before a third agent calls `run_workflow`.

Yes. An agent monitoring the run with `get_run_status` can invoke `cancel_run` if it detects an error or timeout.

Install `autogen-ext[mcp]` and use `mcp_server_tools` with `StreamableHttpServerParams` to fetch the tools. Pass the resulting tool list directly into your `AssistantAgent`.

The `McpToolAdapter` automatically translates the JSON schemas of the tools into the format AutoGen agents expect. This ensures error-free tool calling during conversations.

All execution variables and run histories pass through an isolated V8 sandbox. We do not store, log, or inspect the payloads transmitted between your AutoGen agents and the Relay API.

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