How to Use the Equinix Metal MCP in LlamaIndex

Turn your Equinix Metal configuration into a searchable knowledge base with LlamaIndex. Ask questions, get real answers.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Equinix Metal MCP to LlamaIndex

Create your Vinkius account to connect Equinix Metal 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 Equinix Metal with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Infrastructure State

This server lets your LlamaIndex agent call tools to manage Equinix Metal credentials and then indexes the results. When your agent runs `create_project_api_key`, the output—the key's token, description, and creation date—is automatically fed into a vector store. Now you can ask natural language questions about your setup. Query your agent: "Show me all project API keys created for the 'staging-build' project last month." It will search the indexed results of past tool calls and give you a precise, fact-based answer.

Audit User Access and Invitations

Stop digging through the console to see who has access. Have your agent periodically call `get_invitation` for all your projects and index the status of each one. The results become part of its knowledge base. This lets you ask your agent things like, "Does anyone from the 'contractor' domain have a pending invitation?" or "Who declined an invite last week?" The agent can even use `decline_invitation` if it finds an invite that violates a policy you've defined.

Build a RAG Agent for Your MCP Server

The `McpToolSpec` makes it simple to add these Equinix Metal tools to your LlamaIndex agent. It turns each tool, like `create_user_api_key` or `update_email`, into a function the agent can both call and index. This is how you build a RAG pipeline on live infrastructure data. Your agent doesn't just act; it remembers. Every time it uses `delete_api_key`, that action and its outcome are recorded. This creates a living document of your infrastructure management, grounded in the real-world operations performed by this MCP server.

Setup guide

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

LlamaIndex indexes the output of the tools from this MCP server. This means you can ask your agent questions about your Equinix Metal API keys and invitations in plain English, and it retrieves answers from a history of actual operations.

The tool executes the action on your Equinix Metal account, deleting the key. LlamaIndex then indexes the result of that operation, such as a success confirmation and a timestamp. This gives you a searchable audit log of all actions taken.

Yes, that's a primary use case. By indexing the output of tools like `create_project_api_key` over time, you build a history. You can then ask your LlamaIndex agent, "What were the active keys in Q2?" and get an answer based on the indexed data.

No. The agent can take action. Based on your query, it can decide to execute tools like `delete_api_key` or `decline_invitation`. It's a full loop: query data, reason about it, and then act on your Equinix Metal resources.

When your agent uses these tools, sensitive data like API keys and user emails can be indexed and stored in your configured vector database. Securing this data means implementing strict access controls on the vector store itself, as that's where the history of your operations resides.

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