How to Use the Equinix Metal MCP in AutoGen
Use AutoGen's multi-agent debates to make safer, smarter decisions about your Equinix Metal infrastructure.
Works with every AI agent you already use
…and any MCP-compatible client
Connect Equinix Metal MCP to AutoGen
Create your Vinkius account to connect Equinix Metal to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.
Debate Security Policies Before Acting
Give one agent the goal of provisioning a new service. It might propose using `create_user_api_key` for simplicity. But a second agent, acting as a security guard, can intervene. It can argue that a `create_project_api_key` is more secure because it's scoped to a single project. This isn't a simple script; it's a negotiation. The agents converse, weigh the risks, and converge on the better solution before any tool is ever called. The result is infrastructure managed by consensus, not by a single, potentially flawed directive.
Coordinate Complex Team Workflows
Onboard a new team member with an agent conversation. An HR agent can provide the user's details, triggering a DevOps agent to call `create_email` and `get_invitation` to set them up in Equinix Metal. If the invitation is sent to the wrong address, the agent can use `delete_email` and try again. If an issue arises, the agents can adapt. For example, if an invitation isn't accepted, a 'manager' agent could be programmed to follow up. This creates a resilient system where different specialists—your agents—collaborate to get the job done.
Equip Your AutoGen Agents with MCP Server Tools
With the `mcp_server_tools` function, you can instantly give your AutoGen assistants the ability to manage Equinix Metal. You can create specialized agents: a 'KeyManager' agent that can only use `create_project_api_key` and `delete_api_key`, and a 'UserAdmin' agent that handles `update_email`. This lets you enforce separation of duties at the agent level. The agents will then use these tools in conversation to solve problems. It's a more robust way to automate, using debate and specialized roles to prevent common mistakes.
Set up Equinix Metal MCP in AutoGen
Prerequisites
- Python 3.10+ installed
-
autogen-ext[mcp]package - Active Vinkius subscription with a valid endpoint token
- 1
Install AutoGen with MCP
Run
pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includesmcp_server_toolsfor stateless tool access. - 2
Fetch tools from the MCP
Call
mcp_server_tools(SseServerParams(url=...))with your Vinkius endpoint. Replace[YOUR_TOKEN_HERE]with your token from cloud.vinkius.com. - 3
Run your agent
Pass the tools to
AssistantAgentand callagent.run(). The agent invokes Equinix Metal tools and returns structured results.
from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
server_params = SseServerParams(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
tools = await mcp_server_tools(server_params)
agent = AssistantAgent(
name="Equinix Metal_assistant",
model_client=OpenAIChatCompletionClient(model="gpt-4o"),
tools=tools,
)
result = await agent.run("List recent Equinix Metal data")
print(result.messages[-1].content) Prerequisites
- Python 3.10+ installed
-
autogen-ext[mcp]+autogen-agentchat - Active Vinkius subscription with a valid endpoint token
- 1
Install dependencies
Same packages as above.
McpWorkbenchis ideal when your agent needs stateful sessions across multiple tool calls. - 2
Use McpWorkbench as context manager
Wrap your agent in
async with McpWorkbench(...)to maintain shared state and resources. The workbench manages the full MCP session lifecycle. - 3
Run with workbench
Pass
workbench=workbenchto your agent. State is preserved across multiple tool calls within the same session.
from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
server_params = SseServerParams(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
async with McpWorkbench(server_params) as workbench:
agent = AssistantAgent(
name="Equinix Metal_assistant",
model_client=OpenAIChatCompletionClient(model="gpt-4o"),
workbench=workbench,
)
result = await agent.run("List recent Equinix Metal data")
print(result.messages[-1].content) 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.
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 AutoGen
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the Equinix Metal MCP today
We host it, we monitor it, we maintain it. You just paste one token.