How to Use the Metorial MCP in Claude Code

Q: How do I add the Metorial MCP Server to Claude Code?

Run the claude mcp add command with the HTTP transport flag and your Vinkius endpoint URL. It updates your local config instantly.

Q: How do I monitor Metorial costs from Claude Code?

Ask the CLI agent to check your spending, and it will call metorialgetusagemetrics to display the raw dollar amounts.

Manage serverless Metorial infrastructure and inspect execution traces directly from the Claude Code MCP client.

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 Code

Create your Vinkius account to connect Metorial to Claude Code 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipe serverless metrics straight to your shell

`metorial_get_usage_metrics` dumps raw performance data and cost statistics directly into your Claude Code terminal. This lets you pipe Metorial resource metrics into local shell scripts or grep for high-latency calls without leaving Claude Code. It makes monitoring your remote Metorial agent infrastructure feel like checking local system stats in Claude Code. You get fast, unformatted Metorial numbers that are perfect for terminal-based debugging inside Claude Code.

Spin up and tear down nodes from the CLI

`metorial_deploy_server` provisions new serverless logic instances using simple Claude Code terminal commands. You can tell Claude Code to spin up a Metorial node, run a quick test, and immediately destroy it using the Metorial MCP Server. This is perfect for automated Claude Code testing pipelines and quick terminal sessions. You avoid the overhead of heavy web dashboards and keep your entire Metorial development loop inside Claude Code.

Inspect trace boundaries in headless environments

`metorial_list_traces` retrieves the transaction history of your remote Metorial tools directly in your Claude Code shell. Claude Code uses this to find failing Metorial executions and pull their exact parameters. By calling `metorial_get_trace_details` on a specific execution ID, the Claude Code agent displays the raw Metorial inputs and outputs. You can debug complex remote Metorial routing errors in seconds without leaving Claude Code.

Setup guide

Set up Metorial MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see metorial-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Metorial transactions." It will automatically discover and invoke the available Metorial tools.

Terminal

claude mcp add --transport http metorial-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Metorial MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "metorial-mcp": {
      "type": "url",
      "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 Code

Run the `claude mcp add` command with the HTTP transport flag and your Vinkius endpoint URL. It updates your local config instantly.

Yes, since Claude Code runs in the terminal, you can script it to deploy nodes, run tests, and check execution traces automatically.

Ask the CLI agent to check your spending, and it will call `metorial_get_usage_metrics` to display the raw dollar amounts.

Claude Code stores all MCP Server connections in the global config file on your local machine.

All metrics and deployment parameters are locked behind your unique Vinkius token. The CLI client uses secure HTTPS to prevent sniffing on public networks.

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