How to Use the Hexomatic MCP in Google ADK

Q: Can a Gemini agent using Google ADK trigger a specific Hexomatic scraping recipe?

Absolutely. The agent first finds the recipe ID using listscrapingrecipes, then calls runworkflow with that ID. It can inject starting URLs or other variables at runtime.

Q: How do I get results from a Hexomatic run into BigQuery using Google ADK?

Your agent calls getworkflowresults to get the output data. From there, you use the Google Cloud SDK within your agent's code to write that data directly to a BigQuery table.

Q: What's the process for debugging a Hexomatic workflow with a Google ADK agent?

The agent should call getexecutionlogs using the run ID from a runworkflow call. Gemini's reasoning capabilities can then analyze the logs to pinpoint the error or cause of failure.

Q: How do I manage my Hexomatic automation credits with a Gemini agent?

Before starting a large job, have the agent call getaccountusage. The agent can then check the returned credit count against a predefined threshold to ensure you don't exhaust your monthly limit.

Connect Hexomatic data to your Gemini agents and Google Cloud with the Google ADK.

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 Google ADK

Create your Vinkius account to connect Hexomatic to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed BigQuery with Fresh Data

Use a Gemini agent to trigger a Hexomatic scraping job with `run_workflow`. Once the job is done, the agent pulls the structured data using `get_workflow_results` and pipes it straight into a BigQuery table. It's a direct path from web data to your data warehouse. This lets you build fully automated data pipelines on Google Cloud. Your agent can find the right automation with `list_scraping_recipes`, check your credit balance with `get_account_usage`, and manage the entire ETL process without manual intervention.

Enterprise-Scale Automation

The Google ADK is designed for big jobs, and this Hexomatic server is ready for it. Your agent can get an inventory of all your automations with `list_workflows` and then use `update_workflow_status` to activate or deactivate them based on logic running in Vertex AI. Gemini's large context window is a major asset here. Your agent can ingest and analyze the `get_execution_logs` from dozens of runs at once. This helps it spot systemic issues or performance degradation across your entire Hexomatic account.

Control Your Hexomatic MCP Server

Give your agent the keys to manage your Hexomatic account. It can get configuration details with `get_workflow_details` or even list team members with `list_account_teams`. This is about more than just running jobs; it's about operational control. The Google ADK's `McpToolset` gives you fine-grained control. You can choose to expose only a subset of the Hexomatic tools to your agent. For instance, allow it to run workflows but not change their status, enforcing a clear separation of duties.

Setup guide

Set up Hexomatic MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Hexomatic tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Hexomatic_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Hexomatic tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Absolutely. The agent first finds the recipe ID using `list_scraping_recipes`, then calls `run_workflow` with that ID. It can inject starting URLs or other variables at runtime.

Your agent calls `get_workflow_results` to get the output data. From there, you use the Google Cloud SDK within your agent's code to write that data directly to a BigQuery table.

The agent should call `get_execution_logs` using the run ID from a `run_workflow` call. Gemini's reasoning capabilities can then analyze the logs to pinpoint the error or cause of failure.

Before starting a large job, have the agent call `get_account_usage`. The agent can then check the returned credit count against a predefined threshold to ensure you don't exhaust your monthly limit.

No. The server acts as a secure pass-through. Your agent's requests and Hexomatic's responses, including workflow output data, are processed in isolated sandboxes and are not persisted by Vinkius.

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