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

Q: Can Cursor help me clean up stuck runs using Modal (Serverless AI Infrastructure)?

Yes, the editor can use stopapp to terminate any running application immediately. This prevents runaway compute costs when a prototype container gets stuck in an infinite loop.

Q: How does the Modal (Serverless AI Infrastructure) MCP Server integrate with Cursor Agent mode?

The agent invokes tools like listdeployments to inspect live container states and match them to your local code. This lets the AI write accurate integration scripts based on real deployment metadata.

Q: Does this tool support mounting new network storage volumes?

No, this is an inspection tool. You can use listvolumes to view active network storage, but you must define and mount new volumes within your Python deployment code.

Run, monitor, and audit serverless GPU deployments on Modal while writing code 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 Modal (Serverless AI Infrastructure) MCP to Cursor

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track live serverless state inside the Cursor editor

The `list_apps` tool fetches all active and historical container runs directly into your active coding session. Your Cursor agent reads this execution history to troubleshoot runtime errors without forcing you to open a terminal. When a container behaves unexpectedly, your editor uses `get_app` to inspect the exact static details of that specific run. This gives the AI the exact context it needs to modify your local code and fix deployment issues.

Verify storage volumes and secrets with your MCP Server

The `list_volumes` tool lists your persisted network block storage volumes to check current disk allocations. Cursor reads this data to verify that your large language model weights are mounted to the correct paths. To check environment variables, `list_secrets` provides a list of active configuration references. Your agent cross-references these names with your code imports to ensure your serverless functions have the required keys.

Audit promoted production deployments in Agent mode

The `list_deployments` tool retrieves your promoted production endpoints directly inside the chat pane. Cursor uses this information to map out your active API architecture while you write client-side integration code. If you need to inspect a specific production model, `get_deployment` pulls its exact GPU and container configuration. This lets you verify live deployment states without leaving your workspace or switching contexts.

Setup guide

Set up Modal (Serverless AI Infrastructure) 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 Modal (Serverless AI Infrastructure) 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 Modal (Serverless AI Infrastructure) transactions." If the MCP tools are loaded correctly, Cursor will call the Modal (Serverless AI Infrastructure) tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

Create an mcp.json file in your project root or global directory and add the server configuration. Enable Agent mode in the chat interface to let the editor invoke the serverless tools.

Yes, the editor can use stop_app to terminate any running application immediately. This prevents runaway compute costs when a prototype container gets stuck in an infinite loop.

The agent invokes tools like list_deployments to inspect live container states and match them to your local code. This lets the AI write accurate integration scripts based on real deployment metadata.

No, this is an inspection tool. You can use list_volumes to view active network storage, but you must define and mount new volumes within your Python deployment code.

Your app metadata, volume names, and secret references remain strictly within your local editor context. The MCP protocol processes these queries locally, ensuring your private cloud architecture is never exposed to external databases.

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