How to Use the Hexomatic MCP in LlamaIndex

Q: How can LlamaIndex use data from a Hexomatic workflow?

Your agent calls runworkflow and then getworkflowresults. The structured data from Hexomatic is then passed to a LlamaIndex reader or directly indexed, making it available for semantic search in your RAG pipeline.

Q: Can a LlamaIndex agent decide which Hexomatic scraping recipe to run?

Yes. You expose tools like listscrapingrecipes and searchworkflows to the agent. It can then reason about which recipe is best suited to answer a user's query and execute it automatically.

Q: How do I keep my Hexomatic data fresh in my LlamaIndex app?

Set up an agent to periodically run key workflows using runworkflow. It fetches the new data with getworkflowresults and re-indexes it, keeping your knowledge base current.

Q: Can I check my Hexomatic credit usage from my LlamaIndex agent?

Yes, the getaccountusage tool is for exactly that. Your agent can check its remaining credits before deciding to run a potentially expensive workflow.

Turn Hexomatic's web data into a searchable knowledge base for your LlamaIndex RAG agent.

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 LlamaIndex

Create your Vinkius account to connect Hexomatic to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Live Web Data on Demand

Let your agent find and run a scraping job with `search_workflows` and `run_workflow`. It can trigger a Hexomatic recipe to get the latest information from any website, like product prices or news headlines. The real work happens next. Your agent takes the output from `get_workflow_results` and automatically indexes it into a vector store. Now your RAG application can answer questions using real-time data, not just stale documents.

Build a Self-Updating Knowledge Base with this MCP Server

You can create a query engine that knows about its own automation capabilities. It can use `list_scraping_recipes` and `get_workflow_details` to understand what kind of data it can fetch from the web. This allows the agent to answer questions like, "What scraping recipes do we have for social media profiles?" The answers are grounded in the actual, current state of your Hexomatic account. It's a knowledge base about your own automation toolkit.

Monitor Costs and Performance

Running lots of scraping jobs can get expensive. Your agent can use `get_account_usage` before triggering a big job with `run_workflow`. This prevents unexpected credit usage. If a query returns strange results, the agent can trace it back to the source. It can use `get_execution_logs` to check the health of the Hexomatic run that produced the data, ensuring the knowledge base isn't polluted with bad information.

Setup guide

Set up Hexomatic MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Hexomatic MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Hexomatic tools.",
)
response = await agent.run("List recent Hexomatic data")

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 LlamaIndex

Your agent calls `run_workflow` and then `get_workflow_results`. The structured data from Hexomatic is then passed to a LlamaIndex reader or directly indexed, making it available for semantic search in your RAG pipeline.

Yes. You expose tools like `list_scraping_recipes` and `search_workflows` to the agent. It can then reason about which recipe is best suited to answer a user's query and execute it automatically.

Set up an agent to periodically run key workflows using `run_workflow`. It fetches the new data with `get_workflow_results` and re-indexes it, keeping your knowledge base current.

Yes, the `get_account_usage` tool is for exactly that. Your agent can check its remaining credits before deciding to run a potentially expensive workflow.

Only the data your agent requests. When you run a workflow, you might send input URLs. The server only handles the IDs and parameters needed for the API calls, and your scraped data is retrieved on-demand. Vinkius ensures the connection is isolated and doesn't persist your data.

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