How to Use the Metorial MCP in Cursor

Q: How do I add Metorial to my Cursor configuration?

Create a .cursor/mcp.json file in your project root and add the Metorial server configuration. Cursor will automatically detect the settings and enable the tools for your next coding session.

Q: Can I use the Metorial MCP Server to test code inside Cursor?

Yes, the agent can trigger metorialinvokeservertool to run tests on your remote serverless containers. This lets you verify code behavior against actual live environments without leaving your editor.

Q: Does Metorial support global setup in Cursor?

Yes, you can configure Metorial in your global /.cursor/mcp.json file so that the serverless management tools are available across all your local coding projects.

Q: How does the Metorial MCP Server execute tools inside Cursor?

It sends execution payloads via metorialinvokeservertool to your active serverless container. Cursor parses the response inline, allowing the agent to use the live results to write the next block of code.

Code with live serverless infrastructure and debug execution traces using this MCP Server in Cursor.

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 Cursor

Create your Vinkius account to connect Metorial to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Provision remote test servers inside Cursor

This feature uses `metorial_deploy_server` and `metorial_list_servers` to let Cursor deploy live backend test nodes as you write code. Instead of mocking API endpoints, your editor spins up actual serverless containers to run integration tests on the fly. You can instantly see your active inventory of testing nodes inside the editor. It allows Cursor to write code against live, real-world infrastructure rather than stale local stubs.

Analyze runtime performance with this MCP Server

This feature uses `metorial_get_usage_metrics` and `metorial_get_server_status` to feed live performance data directly to Cursor. The editor monitors memory allocation, execution latency, and hosting costs of your serverless environments while you refactor. Having these metrics inside your coding environment helps you optimize cold starts. You can make immediate adjustments to your resource limits based on actual telemetry.

Inspect failing execution paths in the editor

This feature uses `metorial_get_trace_details` and `metorial_list_traces` to pull failing tool execution logs right into your Cursor chat. When a remote run fails, Cursor scans the exact transaction boundary to show you the error trace. You do not have to switch to an external browser tab to find out why a tool failed. The raw error logs display inline, letting you patch the code and run the tool again immediately.

Setup guide

Set up Metorial MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Metorial MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Metorial transactions." If the MCP tools are loaded correctly, Cursor will call the Metorial tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

Create a `.cursor/mcp.json` file in your project root and add the Metorial server configuration. Cursor will automatically detect the settings and enable the tools for your next coding session.

Yes, the agent can trigger `metorial_invoke_server_tool` to run tests on your remote serverless containers. This lets you verify code behavior against actual live environments without leaving your editor.

Yes, you can configure Metorial in your global ~/.cursor/mcp.json file so that the serverless management tools are available across all your local coding projects.

It sends execution payloads via `metorial_invoke_server_tool` to your active serverless container. Cursor parses the response inline, allowing the agent to use the live results to write the next block of code.

Metorial isolates all usage metrics and server statuses behind secure workspace tokens. Only authorized Cursor clients with matching credentials can call `metorial_get_usage_metrics`, ensuring your infrastructure costs and performance data remain completely confidential.

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