How to Use the Modal (Serverless AI Infrastructure) MCP in VS Code Copilot

Q: Can VS Code Copilot track active GPU resources using the Modal (Serverless AI Infrastructure) MCP Server?

Yes, Copilot calls listdeployments and getdeployment to inspect active GPU allocations. This lets your team monitor hardware usage and scaling configurations directly from the editor.

Q: How does the Modal (Serverless AI Infrastructure) MCP Server handle running containers inside VS Code Copilot?

The server exposes listapps and getapp to let Copilot monitor container lifecycles. Your team can track active runtimes and kill stuck processes with simple chat commands.

Q: Can we edit secret values using this extension?

No, editing is not supported. The listsecrets tool only lists the names of active configurations to help you verify setup without risking credential exposure.

Monitor serverless GPU workloads and manage Modal deployments directly within VS Code Copilot.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Modal (Serverless AI Infrastructure) MCP to VS Code Copilot

Create your Vinkius account to connect Modal (Serverless AI Infrastructure) to VS Code Copilot 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 Modal (Serverless AI Infrastructure) with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit serverless apps directly in VS Code Copilot

The `list_apps` tool retrieves active and historical container runs to give your development team instant visibility. VS Code Copilot checks this real-time execution list to help you debug failing serverless functions on Modal. If a test run goes rogue, your team can use `stop_app` to kill the container execution. This direct terminal-free control prevents budget overruns during collaborative debugging sessions.

Verify production deployments with this MCP Server

The `list_deployments` tool pulls your active, promoted production models directly into the Copilot chat panel. This helps your team verify which API versions are live without leaving the shared codebase. For deep architectural audits, `get_deployment` inspects the specific GPU and container settings of any live endpoint. Copilot reads these details to help you optimize cold-start performance and resource allocation.

Inspect shared volumes and secret configurations

The `list_volumes` tool displays your persisted network block volumes to verify disk mounts across your team. Copilot uses this data to make sure your serverless apps are reading from the correct storage paths. To verify environment settings, `list_secrets` lists the names of your active secret configurations. This allows the team to confirm that required credentials are bound to the environment without exposing raw values.

Setup guide

Set up Modal (Serverless AI Infrastructure) MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Modal (Serverless AI Infrastructure) MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Modal (Serverless AI Infrastructure) tools listed. Try asking: "List my recent Modal (Serverless AI Infrastructure) transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "modal-serverless-ai-infrastructure-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 Modal. 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 Modal (Serverless AI Infrastructure) 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 Modal (Serverless AI Infrastructure) MCP in VS Code Copilot

You can commit an mcp.json file inside the .vscode folder of your repository. Every developer on your team will automatically get access to the same serverless management tools.

Yes, Copilot calls list_deployments and get_deployment to inspect active GPU allocations. This lets your team monitor hardware usage and scaling configurations directly from the editor.

The server exposes list_apps and get_app to let Copilot monitor container lifecycles. Your team can track active runtimes and kill stuck processes with simple chat commands.

No, editing is not supported. The list_secrets tool only lists the names of active configurations to help you verify setup without risking credential exposure.

All communication with the serverless API occurs locally on your machine or within your secure container environment. Your app IDs, volume states, and deployment references are never stored on external servers.

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