An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Modal Serverless AI Infrastructure to your AI

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage GPU deployments and compute resources through natural conversation.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 7 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 7 available through Modal.

  1. 01

    List secrets

    This capability lists your static secret dictionary configuration references. Use it to verify environment variable mappings for your functions.

  2. 02

    Stop app

    This capability forces an active Modal App execution to stop. Use it to kill runaway processes and prevent unnecessary billing.

  3. 03

    List apps

    This capability shows your isolated active and historical Modal App contexts. It is the quickest way to see what is currently running.

  4. 04

    Get app

    This capability pulls the static specifics for a single Modal App ID. It returns the precise metadata for a specific application.

Capability set02 / 02

05-07

3 capabilities in this set.

Part of 7 available through Modal.

  1. 05

    List volumes

    This capability retrieves a list of your Modal persisted disk network block volumes. It helps you track available storage across distributed instances.

  2. 06

    List deployments

    This capability enumerates your promoted Modal platform deployments. Use it to see all your managed, long-running services.

  3. 07

    Get deployment

    This capability fetches specific details for a tracked deployment. It provides the mapping and configuration for your promoted services.

Real work

What teams actually run

01

GPU Job Monitoring

Check the status of a long-running training job while you continue coding in your IDE.

02

Cost Control

Stop an active Modal app immediately if you notice it is consuming more resources than intended.

03

Storage Audits

Verify that your data mount directories and persistent volumes are correctly configured for your distributed compute.

04

Deployment Verification

Retrieve the specific web endpoints for your promoted deployments to test new service versions.

Automate a task

Put Modal to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Modal works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Modal to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

836ms average. Fast in production.

Modal is checked daily against the live service.

Daily averagePeak 1064ms
Oct 3Today
Fastest day
705ms
Slowest day
1064ms
14-day trend
Slowing+28%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 7 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Modal, so you can see the experience inside your AI.

It does not authenticate your account with Modal. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Modal Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_yQfuiuyaifaMlCchZoeV6rYy4ok4PpgYEfzlMmar/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Modal capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "modal-serverless-ai-infrastructure-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_yQfuiuyaifaMlCchZoeV6rYy4ok4PpgYEfzlMmar/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Modal in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Modal owners hand off.

This MCP is built for engineers working with high-performance serverless compute.

  • 01

    AI Engineers

    They use the agent to monitor GPU training jobs and check deployment endpoints without using the CLI.

  • 02

    Data Scientists

    They use the agent to audit persistent volumes and check function logs from their workspace.

  • 03

    DevOps Teams

    They use the agent to manage serverless secrets and track resource usage across projects.

FAQ

Questions Modal owners ask.

  • 01

    How do I stop a running Modal app using this MCP?

    You can tell your AI client to stop a specific app by providing its App ID. The agent will use the stop_app capability to terminate the execution and prevent further billing.

  • 02

    Can I see my storage volumes through my AI agent?

    Yes. You can ask your agent to list your persistent disk network block volumes using the list_volumes capability.

  • 03

    Which AI clients are compatible with this MCP?

    This MCP works with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 04

    Do I need to use the Modal CLI to manage my apps?

    No. This MCP allows you to perform tasks like listing apps, stopping executions, and checking deployments through your AI client instead of the CLI.

  • 05

    Is my Modal credential information secure?

    Yes. Vinkius hosts the MCP and manages your credentials securely so you can connect your client once and start working.

  • 06

    Can I stop a running Modal app through my agent to save costs?

    Yes. Use the stop_app capability with an active App ID. Your agent will dispatch a termination command to Modal, gracefully stopping the serverless container spin-up and preventing further billing for that specific execution.

  • 07

    How do I check which web endpoints are active for my deployments?

    The list_deployments and get_deployment capabilities retrieve the Promoted image data. Your agent will expose the public URL endpoints and serving metadata associated with your long-running Modal deployments.

  • 08

    Can my agent audit the secrets and persistent volumes in my workspace?

    Absolutely. Use the list_secrets and list_volumes capabilities to monitor your infrastructure assets. Your agent will report the names and references for your stored secrets and network block storage mounts attached to your compute instances.

Explore

More in Superpower

Suggestions

Connect Modal to Claude, Cursor, ChatGPT & more