How to Use the Equinix Metal MCP in LangChain

Q: Can I combine these Equinix Metal tools with other LangChain integrations?

Yes, that's the point. Create a project API key with createprojectapikey, then have the next step in the chain use a different tool to store that key in HashiCorp Vault or AWS Secrets Manager. This MCP server handles the Equinix Metal part.

Q: How do I handle errors when managing Equinix Metal resources with LangChain?

LangChain's error handling wraps the tool calls. If createprojectapikey fails due to a permissions issue, the exception is caught in your chain. You can then build logic for retries or send a notification to a Slack channel.

Build observable, chained workflows for Equinix Metal with LangChain. Stop managing infrastructure by hand.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate API Key Rotation

This MCP server gives your agent the tools to manage Equinix Metal API keys. You can build a LangChain agent that runs on a schedule, calls `create_project_api_key` to generate a new key, pushes it to your secret manager, and then immediately calls `delete_api_key` on the old one. It's a simple, reliable chain. Because it’s LangChain, every step is traced in LangSmith. You see the exact inputs and outputs for each tool call. You'll know precisely which key was created and which was deleted, with timestamps, giving you a full audit trail for your security team.

Manage Team Onboarding and Access

Use a chain to handle new user invitations. Your agent can get a list of pending invites, call `get_invitation` to check the status of a specific user, and then decide what to do next. If an invitation is old or was sent to the wrong person, the agent can use `decline_invitation` to revoke it automatically. You can also manage user contact info. A chain can be triggered to call `create_email` when a new user joins, or use `update_email` to set their primary contact method. This keeps your Equinix Metal user directory in sync with your source of truth.

Your Equinix Metal LangChain Toolkit

This isn't just a random collection of API calls. The tools are designed to work together as steps in a larger process. Once you connect the MCP server, you get a set of functions your agent can reason about and execute in logical order. Your agent isn't just running one-off commands; it's executing a plan. Your agent can now build, manage, and tear down access credentials programmatically. It can handle user keys with `create_user_api_key` and `delete_user_api_key` as part of a larger CI/CD pipeline or an internal admin bot. It's direct control, right from your code.

Setup guide

Set up Equinix Metal 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 Equinix Metal 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({
    "equinix-metal-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 Equinix Metal 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 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 LangChain

Install the MCP adapter, point it to the Vinkius endpoint, and call `client.get_tools()`. Pass the resulting tool list to your LangChain agent constructor. Your agent now has all nine Equinix Metal functions ready to go.

Create a chain that checks for expired API keys. The agent can list keys (using a different tool), find an expired one, and use `delete_api_key` from this server to remove it. It’s a direct, automated cleanup task.

Yes, that's the point. Create a project API key with `create_project_api_key`, then have the next step in the chain use a different tool to store that key in HashiCorp Vault or AWS Secrets Manager. This MCP server handles the Equinix Metal part.

LangChain's error handling wraps the tool calls. If `create_project_api_key` fails due to a permissions issue, the exception is caught in your chain. You can then build logic for retries or send a notification to a Slack channel.

The API keys, email addresses, and invitation details you work with pass through the LangChain framework. If you're using LangSmith, this data will appear in your traces. Your security responsibility is to lock down access to your LangChain environment and any connected logging platforms.

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