How to Use the Metorial MCP in Claude

Q: How do I configure Metorial inside Claude Desktop?

Open your claudedesktopconfig.json file and add the Metorial credentials under the server configuration key. Once you restart the app, Claude Desktop can immediately invoke metoriallistservers to see your running instances.

Q: How does the Metorial MCP Server handle tool execution in Claude Desktop?

It uses metorialinvokeservertool to route your commands directly to the hosted container node. Claude Desktop sends the payload, the remote container runs the task, and the results stream back to your chat.

Run remote serverless nodes and monitor execution traces using this MCP Server in Claude Desktop.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Metorial MCP to Claude Desktop

Create your Vinkius account to connect Metorial to Claude Desktop 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 Metorial with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Spin up serverless runtimes inside Claude Desktop

This integration uses `metorial_deploy_server` and `metorial_delete_server` to provision or tear down isolated serverless instances directly from your chat window. When you ask Claude Desktop to spin up a new node, it talks to the Metorial API to configure the infrastructure instantly. You can quickly clean up dead resources using `metorial_delete_server` without leaving your workspace. It keeps your remote environment clean without manual dashboard diving.

Check node health with this MCP Server

This feature uses `metorial_get_server_status` and `metorial_list_servers` to give Claude Desktop a live view of your active endpoints. Your agent polls these tools to verify which instances are running before attempting to route commands. If a node goes offline, Claude Desktop reads the status directly and alerts you. You get instant visibility into your running inventory without running terminal commands.

Debug agent steps using trace logs

This feature uses `metorial_get_trace_details` and `metorial_list_traces` to pull execution logs directly into your Claude Desktop conversation. When an agent action fails, Claude reads the raw transaction boundaries to pinpoint the exact line of code that broke. By examining these trace details, you can fix prompt logic or tool arguments on the fly. It turns your chat client into a live debugger for complex agent workflows.

Setup guide

Set up Metorial MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Metorial MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Metorial MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under metorial-mcp.

json

{
  "mcpServers": {
    "metorial-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Metorial. 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 Metorial 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 Metorial MCP in Claude Desktop

Open your `claude_desktop_config.json` file and add the Metorial credentials under the server configuration key. Once you restart the app, Claude Desktop can immediately invoke `metorial_list_servers` to see your running instances.

Yes, when you ask the agent to create a runtime, it executes `metorial_deploy_server` behind the scenes. This provisions the serverless container instantly and registers it to your active workspace list.

No, Metorial is designed for remote serverless environments, meaning Claude Desktop connects to it over a secured HTTPS endpoint. This keeps your local machine free from heavy runtime overhead.

It uses `metorial_invoke_server_tool` to route your commands directly to the hosted container node. Claude Desktop sends the payload, the remote container runs the task, and the results stream back to your chat.

Your execution traces and tool parameters are stored in an encrypted database isolated to your workspace. Metorial secures these transaction logs so that only authorized calls to `metorial_get_trace_details` can read them, keeping your sensitive data private.

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