How to Use the Hetzner MCP in LlamaIndex

Q: How do I add Hetzner MCP tools to LlamaIndex?

Run pip install llama-index-tools-mcp. Configure a BasicMCPClient with your Vinkius URL, wrap it in an McpToolSpec, and call totoollistasync() to feed the tools into your FunctionAgent.

Q: Can LlamaIndex filter which Hetzner tools are available?

You restrict access using the allowedtools parameter during initialization. If you only want the agent to read data, you limit it to tools like listservers and listdatacenters while blocking deleteserver.

Q: Can I use LlamaIndex to deploy new Hetzner servers?

Yes. While LlamaIndex excels at RAG, the FunctionAgent can execute write operations like createserver or createsshkey if you include those specific functions in your tool specification.

Index your Hetzner Cloud topology in LlamaIndex to query live server states and network configurations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hetzner MCP to LlamaIndex

Create your Vinkius account to connect Hetzner 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 Hetzner with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Live Infrastructure with the MCP Server

This Hetzner MCP server connects your LlamaIndex pipelines directly to your cloud environment. Instead of guessing what runs where, your agent calls `list_servers` and `list_networks`, feeding the live API responses straight into your vector store. You query your actual infrastructure state, not outdated documentation. The setup converts complex JSON responses into semantic nodes. When a developer asks about internal IPs, LlamaIndex retrieves the exact routing tables generated by `list_primary_ips`. You build RAG applications that ground their answers in the physical reality of your deployment.

Query Firewall and Security Postures

Auditing security rules manually burns engineering hours. By exposing `list_firewalls` and `list_certificates` to LlamaIndex, your agent maintains a searchable index of your exact security posture. You just ask which servers expose port 22 to the public internet. The agent cross-references the firewall rules against the nodes returned by `get_server`. It identifies vulnerabilities by reading the actual configurations applied to your infrastructure. Security teams get immediate answers backed by live data rather than static spreadsheets.

Semantic Search for Storage Boxes

Keeping track of backup locations and storage protocols gets messy as teams scale. Your LlamaIndex agent uses `list_storage_boxes` and `list_storage_box_snapshots` to build a complete map of your persistent data. Finding a specific backup takes seconds. If a user needs to know which subaccounts have WebDAV enabled, the agent queries the index built from `list_storage_box_subaccounts`. You stop hunting through the web console and start treating your storage infrastructure as a fully queryable database.

Setup guide

Set up Hetzner 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 Hetzner 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 Hetzner tools.",
)
response = await agent.run("List recent Hetzner 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 Hetzner Cloud. 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 Hetzner 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 Hetzner MCP in LlamaIndex

Run `pip install llama-index-tools-mcp`. Configure a `BasicMCPClient` with your Vinkius URL, wrap it in an `McpToolSpec`, and call `to_tool_list_async()` to feed the tools into your `FunctionAgent`.

You restrict access using the `allowed_tools` parameter during initialization. If you only want the agent to read data, you limit it to tools like `list_servers` and `list_datacenters` while blocking `delete_server`.

The framework indexes the output of the MCP tool calls at the moment of execution. To keep your RAG application accurate, you schedule routine updates that pull fresh data from `list_volumes` and `list_floating_ips`.

Yes. While LlamaIndex excels at RAG, the `FunctionAgent` can execute write operations like `create_server` or `create_ssh_key` if you include those specific functions in your tool specification.

The server processes sensitive topology details, including DNS zones, firewall configurations, and storage subaccount credentials. Vinkius routes these requests through a zero-trust architecture, ensuring no operational data persists after the API call completes.

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