How to Use the Hexomatic MCP in LangChain

Q: How do I run a specific Hexomatic workflow from LangChain?

Your agent should first use listworkflows or searchworkflows to find the correct workflow ID. Then, it calls runworkflow with that ID and any necessary inputs. You'll get an execution ID back to track the job.

Q: Can a LangChain agent get the data scraped by Hexomatic?

Yes. After a workflow finishes, the agent uses getworkflowresults with the execution ID. This returns the structured data from the scrape, which your chain can then process or pass to another tool.

Q: What's the best way to handle errors when using Hexomatic with LangChain?

Your chain should be designed to handle failures. If a runworkflow call fails or the results look wrong, have the agent call getexecutionlogs. The logs will show what happened, so the agent can decide whether to retry or escalate.

Q: Can I build a LangChain agent that chooses which Hexomatic workflow to run on its own?

Absolutely. You provide the agent with tools like searchworkflows and a high-level goal. The ReAct framework in LangChain lets it reason about which workflow best fits the task.

Build LangChain agents that run Hexomatic scraping jobs, check results, and decide what to do next based on the data.

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 LangChain

Create your Vinkius account to connect Hexomatic to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run & Monitor Scraping Workflows

The `run_workflow` tool lets your agent trigger any Hexomatic workflow. You can pass in dynamic inputs, like a list of URLs from a previous step in your chain, to start a scraping job. It's not a fire-and-forget operation. Your agent can then poll for completion and use `get_workflow_results` to get the structured data back. If something looks off, it can pull the `get_execution_logs` to debug the run. This creates a complete loop: run, check, act.

Build Self-Managing LangChain Agents

Your agent can manage its own automation tasks. It uses `list_workflows` and `search_workflows` to find the right tool for the job. No more hardcoding workflow IDs. Based on its goals, the agent can then use `update_workflow_status` to activate a workflow before running it, or deactivate it when it's no longer needed. It can even check `get_account_usage` to make sure it's not about to blow through your credits, adding a layer of cost control to your chain.

Chain Hexomatic with Other Data Sources

This MCP Server connects Hexomatic's scraping power into the LangChain ecosystem. You can build a chain that pulls initial data from a database, uses `run_workflow` to enrich it with fresh web data, and then passes the combined result to another model for analysis. The agent decides the sequence. It might use `list_scraping_recipes` to find a specific recipe, then `run_workflow` to execute it, and finally `get_workflow_results` to feed into a different tool. Each tool call is just one link in a longer reasoning process.

Setup guide

Set up Hexomatic MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Hexomatic tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "hexomatic-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Hexomatic transactions"
    })
    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 LangChain

Your agent should first use `list_workflows` or `search_workflows` to find the correct workflow ID. Then, it calls `run_workflow` with that ID and any necessary inputs. You'll get an execution ID back to track the job.

Yes. After a workflow finishes, the agent uses `get_workflow_results` with the execution ID. This returns the structured data from the scrape, which your chain can then process or pass to another tool.

Your chain should be designed to handle failures. If a `run_workflow` call fails or the results look wrong, have the agent call `get_execution_logs`. The logs will show what happened, so the agent can decide whether to retry or escalate.

Absolutely. You provide the agent with tools like `search_workflows` and a high-level goal. The ReAct framework in LangChain lets it reason about which workflow best fits the task.

The MCP server only processes workflow IDs, execution IDs, and any input data you explicitly provide to `run_workflow`. Your Hexomatic credentials and scraped data stay within their system, accessed on-demand via Vinkius's secure, ephemeral environment. The server itself stores nothing.

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