How to Use the Hexomatic MCP in AutoGen

Q: Can one AutoGen agent run a Hexomatic workflow and another check the results?

Exactly. You can have an 'executor' agent that calls runworkflow and a separate 'validator' agent that uses getworkflowresults and getexecutionlogs to confirm the job ran correctly. They then report their findings back to the group.

Q: Is it possible for AutoGen agents to manage Hexomatic workflow statuses?

Yes, the updateworkflowstatus tool lets an agent activate or deactivate a workflow. This is useful for a 'manager' agent that prepares the environment before an 'executor' agent runs a job.

Let your AutoGen agents debate and agree on the best Hexomatic workflow to run for any task.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hexomatic MCP to AutoGen

Create your Vinkius account to connect Hexomatic 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 Hexomatic with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate via Agent Consensus

Give one agent the `search_workflows` tool and another the `get_account_usage` tool. One agent can propose running a big scraping job, while the other can push back, citing the cost in automation credits. They have to agree before `run_workflow` is ever called. This multi-agent conversation prevents rash actions. An 'engineering' agent might use `get_workflow_details` to check a workflow's configuration, while a 'finance' agent checks the cost. The final action is a result of their negotiation.

Build Specialist Agents with this MCP Server

You can build a team of agents with different roles. An 'Analyst' agent uses `get_workflow_results` to interpret data. A 'QA' agent is responsible for checking `get_execution_logs` to flag any failed runs. A 'Scheduler' agent can use `update_workflow_status` to activate workflows as needed. These agents talk to each other. The QA agent might tell the Analyst not to trust a specific data set because the logs show errors. This creates a resilient system where different agents provide checks and balances on each other.

Manage Your Hexomatic Account with AutoGen

Go beyond just running workflows. Your agents can do account admin. They can use `list_automations` to see what's available or `list_scraping_recipes` to catalog all the custom scrapers your team has built. An administrative agent could even manage collaborators by reviewing the output of `list_account_teams`. The agents work together to not just use, but also organize and maintain your Hexomatic workspace, all through conversational debate.

Setup guide

Set up Hexomatic 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 Hexomatic 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="Hexomatic_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Hexomatic 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="Hexomatic_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Hexomatic 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 Hexomatic. 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 Hexomatic 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 Hexomatic MCP in AutoGen

You assign different Hexomatic tools to different agents. One agent might propose a workflow with `search_workflows`, and another can critique that choice before the group agrees to call `run_workflow`.

Exactly. You can have an 'executor' agent that calls `run_workflow` and a separate 'validator' agent that uses `get_workflow_results` and `get_execution_logs` to confirm the job ran correctly. They then report their findings back to the group.

Create a 'finance' agent whose only job is to watch the budget. Give it the `get_account_usage` tool and instruct it to halt any plan that exceeds a certain credit cost. This agent will argue against expensive runs proposed by other agents.

Yes, the `update_workflow_status` tool lets an agent activate or deactivate a workflow. This is useful for a 'manager' agent that prepares the environment before an 'executor' agent runs a job.

The connection is stateless. The MCP server passes your agents' requests—like a workflow ID for `run_workflow`—to Hexomatic and returns the response. No scraped data or Hexomatic account details are stored on the Vinkius server itself.

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