How to Use the Modal (Serverless AI Infrastructure) MCP in Claude

Q: How does the Modal (Serverless AI Infrastructure) MCP Server help with GPU deployment tracking in Claude Desktop?

The server exposes listdeployments and getdeployment directly to your agent. This lets the chat client inspect your active model endpoints, check GPU configurations, and report back status details.

Q: Can I view my actual environment secret values through this server?

No, you cannot view raw values. The listsecrets tool only returns the names and metadata of your secret dictionaries to protect your production credentials.

Spin up and monitor serverless GPU deployments on Modal right from your Claude Desktop chat interface.

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 Claude Desktop

Create your Vinkius account to connect Modal (Serverless AI Infrastructure) 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 Modal (Serverless AI Infrastructure) with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Modal Serverless Apps directly in Claude Desktop

The `list_apps` tool fetches your active and historical serverless application runs directly inside your Claude Desktop window. You don't have to jump to the web console or run CLI commands to see what's currently executing on Modal's infrastructure. If a run hangs or consumes too many resources, your agent can use `stop_app` to kill the execution immediately. This direct control keeps your compute bills predictable without requiring you to switch windows.

Inspect deployments and track GPU configurations

The `list_deployments` tool retrieves your active, promoted production deployments from the platform. Your agent reads this list to verify which models are live and what endpoints are exposed. When you need deep technical details, `get_deployment` pulls the exact configuration of a specific run. Claude Desktop displays these raw specifications so you can verify GPU allocations or cold-start settings on the fly.

Audit storage and secrets using your MCP Server

The `list_volumes` tool scans your persisted network block volumes to verify disk mounts and storage allocations. Your agent matches these volumes to your serverless containers to make sure your model weights are mapped correctly. For environment configurations, `list_secrets` pulls the names of your active secret dictionaries. Claude Desktop displays these references without exposing the raw values, keeping your production credentials safe while debugging.

Setup guide

Set up Modal (Serverless AI Infrastructure) 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 Modal (Serverless AI Infrastructure) 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 Modal (Serverless AI Infrastructure) 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 modal-serverless-ai-infrastructure-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 Claude Desktop

Open your local configuration file and add the server definition under the mcpServers key. Restart your desktop app, and the serverless tools will show up under the hammer icon in your chat window.

Yes, the agent can stop any active container run using the stop_app tool. You just need to provide the specific application ID in the chat, and the agent kills the process instantly.

The server exposes list_deployments and get_deployment directly to your agent. This lets the chat client inspect your active model endpoints, check GPU configurations, and report back status details.

No, you cannot view raw values. The list_secrets tool only returns the names and metadata of your secret dictionaries to protect your production credentials.

This local setup only routes your Modal app IDs, volume names, and deployment statuses directly through your local Claude Desktop client. No third-party servers store or intercept your serverless configuration details.

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