How to Use the Hexomatic MCP in OpenAI Agents SDK

Q: How do I run a Hexomatic workflow with the OpenAI Agents SDK?

Your agent calls the runworkflow tool. You can pass runtime inputs, like a list of URLs, in the bodyjson parameter. The SDK handles the API call and returns the execution ID.

Q: Can my OpenAI agent check Hexomatic credits before running a task?

Yes. Have your agent call the getaccountusage tool. It returns your current automation credit balance, so the agent can decide whether to proceed with a costly workflow.

Q: How can I debug a failed Hexomatic workflow using the OpenAI Agents SDK?

After a run, your agent can call getexecutionlogs with the workflow's execution ID. This provides a detailed log of the run, which the agent can analyze to identify the point of failure.

Q: What's the best way to find a specific workflow ID in Hexomatic for my agent?

Use the listworkflows tool to get a full list of all workflows and their IDs in your account. For more targeted lookups, your agent can use searchworkflows to find one by its title.

Q: How is data privacy handled when my OpenAI agent accesses Hexomatic workflow results?

When your agent uses getworkflowresults, the resulting data is streamed directly to your agent through Vinkius's ephemeral, zero-trust infrastructure. The data passes through, but it's not stored or analyzed on the MCP server itself.

Build production-ready agents that run Hexomatic automations with the OpenAI Agents SDK.

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 OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Scraping Workflows Safely

Let your agent trigger complex Hexomatic automations using `run_workflow`. Before it starts, the agent can check `get_account_usage` to make sure there are enough credits for the job. This prevents budget overruns before they happen. OpenAI's framework is built for this. You can have one specialized agent find the right scraping recipe with `list_scraping_recipes`, then hand off to another agent to execute the run. A third agent can then pull the final data using `get_workflow_results`, with the entire sequence traced in your dashboard.

Manage Hexomatic from Your Agent

Your agent can do more than just run jobs. It can actively manage your Hexomatic setup. Give it the ability to check a workflow's configuration with `get_workflow_details` or even toggle automations on and off with `update_workflow_status`. This lets you build self-healing systems. If an agent detects a problem after checking `get_execution_logs`, it can automatically deactivate the faulty workflow and notify your team. It’s about giving the agent the tools to solve problems, not just execute tasks.

This MCP Server Works Out of the Box

Connecting this Hexomatic MCP server is simple. The OpenAI Agents SDK automatically discovers all 11 tools as soon as you point it to the Vinkius endpoint. There's no need to manually define functions or handle schemas. Your agent gets a full list of capabilities instantly. It can decide to `search_workflows` to find an automation by name, get its details, check account status, and run it. You just set `cacheToolsList=True` for better performance and let your agent figure out the rest.

Setup guide

Set up Hexomatic 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 Hexomatic tools at runtime.
3

Create your Agent

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

Run the agent

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

Your agent calls the `run_workflow` tool. You can pass runtime inputs, like a list of URLs, in the `body_json` parameter. The SDK handles the API call and returns the execution ID.

Yes. Have your agent call the `get_account_usage` tool. It returns your current automation credit balance, so the agent can decide whether to proceed with a costly workflow.

After a run, your agent can call `get_execution_logs` with the workflow's execution ID. This provides a detailed log of the run, which the agent can analyze to identify the point of failure.

Use the `list_workflows` tool to get a full list of all workflows and their IDs in your account. For more targeted lookups, your agent can use `search_workflows` to find one by its title.

When your agent uses `get_workflow_results`, the resulting data is streamed directly to your agent through Vinkius's ephemeral, zero-trust infrastructure. The data passes through, but it's not stored or analyzed on the MCP 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