Modal (Serverless AI Infrastructure) Connector for AI agents.

Q: How does the Modal MCP help with costs?

It lets you instantly stop active executions using the stopapp tool. This ensures that if a job gets stuck or finishes early, you aren't billed for unnecessary compute time.

Q: Can this stop a runaway training job?

Absolutely. By using the stopapp tool, your agent can forcefully terminate a specific app execution by its ID to save on costs immediately.

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

Yes. Use the stopapp tool 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.

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

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

7 live capabilities

Manage on-demand GPU deployments and high-performance compute resources.

Live agent request Modal (Serverless AI Infrastructure) / Connector

Waiting for input…

AI Agent

Why people use Modal (Serverless AI Infrastructure)

Modal for On-Demand GPU Infrastructure Management

With this Connector, you just ask your agent to "Show me the active deployments." It pulls the URLs, tells you the status, and gives you the metadata in one go. You stay in your workflow instead of hunting through web pages.

What Vinkius changes

You get instant, conversational control over your on-demand GPU infrastructure.

Use it from Claude, ChatGPT, Cursor or another AI client you already have.

One account · 5,900+ Connectors

Real-world use case 01

Stopping a stuck training job

An engineer notices a GPU job is stuck.
Real-world use case 02

Finding new inference endpoints

A dev needs to find the URL for a new inference endpoint.
Real-world use case 03

Verifying storage mounts

A data scientist needs to know if their 200GB dataset volume is mounted.

Complete set · 7capabilities

The complete Modal (Serverless AI Infrastructure) capability set.

These are the exact actions your AI can choose when you ask it to work with Modal (Serverless AI Infrastructure).

Capability set01 / 02

01—04

4 capabilities in this set.

Part of 7 available through Modal (Serverless AI Infrastructure).

01 Capability
List apps
See all your active and historical Modal app contexts in one list. This helps you keep track of what is currently running.
02 Capability
Stop app
Forcefully shut down a running Modal app execution to stop billing immediately. It is the fastest way to kill a stuck job.
03 Capability
List secrets
View the configuration references for your stored secret dictionary. This is useful for auditing your environment variables.
04 Capability
List volumes
See all your persisted disk network block volumes across your compute. This helps you manage your distributed storage.

Capability set02 / 02

05—07

3 capabilities in this set.

Part of 7 available through Modal (Serverless AI Infrastructure).

05 Capability
List deployments
Find all the deployments that have been explicitly promoted on the platform. Use this to see your active serving endpoints.
06 Capability
Get deployment
Fetch the detailed metadata and bound mapping for a specific deployment. It provides the exact web endpoint and config.
07 Capability
Get app
Pull the specific static details for a single Modal App ID. Use this to deep-dive into a specific app's state.

Set up in minutes

One URL. Then ask Modal (Serverless AI Infrastructure) to work.

Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Modal (Serverless AI Infrastructure) from the conversation.

Choose your client

Live preview

Advanced clients IDE · CLI

Claude · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP

https://edge.vinkius.com/vk_preview_yQfuiuyaifaMlCchZoeV6rYy4ok4PpgYEfzlMmar/mcp

Step 01

Open Connectors

In Claude Web or Claude Desktop, open Settings and choose Connectors.
Step 02

Add the URL

Choose Add custom connector, name it Modal (Serverless AI Infrastructure), and paste the URL above.
Step 03

Turn it on in chat

Select +, open Connectors, and enable Modal (Serverless AI Infrastructure) for the conversation.

ChatGPT · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP

https://edge.vinkius.com/vk_preview_yQfuiuyaifaMlCchZoeV6rYy4ok4PpgYEfzlMmar/mcp

Step 01

Open MCP settings

On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
Step 02

Add the URL

Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Modal (Serverless AI Infrastructure) URL.
Step 03

Save and start

Save the connection and enable Modal (Serverless AI Infrastructure) in your conversation. Desktop may ask you to restart once.

Cursor · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "modal-serverless-ai-infrastructure": {
      "url": "https://edge.vinkius.com/vk_preview_yQfuiuyaifaMlCchZoeV6rYy4ok4PpgYEfzlMmar/mcp"
    }
  }
}

Step 01

Open MCP Settings

Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
Step 02

Add the server config

Paste the JSON configuration above into the mcp.json file that opens
Step 03

Save the file

Cursor will automatically detect the new Connector
Step 04

Start using Modal (Serverless AI Infrastructure)

Open Agent mode in chat and ask: "Using Modal (Serverless AI Infrastructure), help me...". 7 tools available

VS Code Copilot · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "modal-serverless-ai-infrastructure": {
      "url": "https://edge.vinkius.com/vk_preview_yQfuiuyaifaMlCchZoeV6rYy4ok4PpgYEfzlMmar/mcp"
    }
  }
}

Step 01

Create MCP config

Create a .vscode/mcp.json file in your project root
Step 02

Add the server config

Paste the JSON configuration above
Step 03

Enable Agent mode

Open GitHub Copilot Chat and switch to Agent mode using the dropdown
Step 04

Start using Modal (Serverless AI Infrastructure)

Ask Copilot: "Using Modal (Serverless AI Infrastructure), help me...". 7 tools available

Windsurf · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "modal-serverless-ai-infrastructure": {
      "url": "https://edge.vinkius.com/vk_preview_yQfuiuyaifaMlCchZoeV6rYy4ok4PpgYEfzlMmar/mcp"
    }
  }
}

Step 01

Open MCP Settings

Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
Step 02

Add the server

Paste the JSON configuration above into mcp_config.json
Step 03

Save and reload

Windsurf will detect the new server automatically
Step 04

Start using Modal (Serverless AI Infrastructure)

Open Cascade and ask: "Using Modal (Serverless AI Infrastructure), help me...". 7 tools available

Cline · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "modal-serverless-ai-infrastructure": {
      "url": "https://edge.vinkius.com/vk_preview_yQfuiuyaifaMlCchZoeV6rYy4ok4PpgYEfzlMmar/mcp"
    }
  }
}

Step 01

Open Cline MCP Settings

Click the Connectors icon in the Cline sidebar panel
Step 02

Add remote server

Click "Add Connector" and paste the configuration above
Step 03

Enable the server

Toggle the server switch to ON
Step 04

Start using Modal (Serverless AI Infrastructure)

Ask Cline: "Using Modal (Serverless AI Infrastructure), help me...". 7 tools available

Claude Code · Terminal command

Official guide ↗

Advanced setup

claude mcp add modal-serverless-ai-infrastructure --transport http "https://edge.vinkius.com/vk_preview_yQfuiuyaifaMlCchZoeV6rYy4ok4PpgYEfzlMmar/mcp"

Step 01

Install Claude Code

Run npm install -g @anthropic-ai/claude-code if not already installed
Step 02

Add the Connector

Run the command above in your terminal
Step 03

Verify the connection

Run claude mcp to list connected servers, or type /mcp inside a session
Step 04

Start using Modal (Serverless AI Infrastructure)

Ask Claude: "Using Modal (Serverless AI Infrastructure), show me...". 7 tools are ready

Where the request belongs

Work Modal can move forward.

Built around the request

AI Engineers and DevOps specialists who are tired of manual CLI polling and want to manage GPU clusters and on-demand functions through a chat interface.

AI Engineer

Checks if a training job is still running and gets the endpoint URL to test the model on a Tuesday afternoon.

Data Scientist

Verifies that the correct persistent volumes are mounted before starting a large dataset processing job.

DevOps Engineer

Audits environment variables and secrets to ensure production deployments are configured correctly.

Build the capability set

Each Connector adds new actions and data without changing how you work.

Browse Connectors

01 7 capabilities

RunPod

Integrate your AI securely to RunPod to cleanly quickly provision scalable GPU pods, manage active instances, and inspect serverless endpoints and custom templates natively.

View Connector

02 7 capabilities

Lambda Labs (GPU Cloud)

Manage AI infrastructure via Lambda Labs. launch GPU instances, monitor ML workloads, and manage SSH keys.

View Connector

03 5 capabilities

Flystack

Manage cloud infrastructure. audit deployments, clusters, and metrics via AI.

View Connector

04 6 capabilities

Paperspace

Provision and track powerful GPU workloads via Paperspace. list compute instances, fetch active deployments, trace team projects, and query Gradient environments via AI.

View Connector

05 9 capabilities

Render

Automate your PaaS infrastructure via Render. list your services, deploy code, check logs, and scale resources directly from any AI agent.

View Connector

06 24 capabilities

Flightcontrol (AWS PaaS Deployments)

Deploy and manage AWS infrastructure via Flightcontrol. list projects, manage environments, and scale services directly from any AI agent.

View Connector

Bring your own AI

Change the model, client or framework. Keep Modal connected.

Claude
ChatGPT
Gemini
Cursor
VS Code
Windsurf
ZCode
Cline
Zed
Continue
Kiro
Roo Code
Zencoder
Goose
Void
Augment Code
Amp
Qodo
Tabnine
Pieces
Sourcegraph Cody
JetBrains
Warp
Amazon Q
Antigravity
BoltAI
Raycast
Jan
LM Studio
AnythingLLM
Open WebUI
Msty
Cherry Studio
LibreChat
TypingMind
Chorus
5ire
n8n
LangChain
LlamaIndex
CrewAI
Vercel AI SDK

Before you connect

Questions about Modal.

The practical details behind the request, access and result.

How does the Modal MCP help with costs?

It lets you instantly stop active executions using the stop_app capability. This ensures that if a job gets stuck or finishes early, you aren't billed for unnecessary compute time.

Can I see my GPU deployment URLs with the Modal MCP?

Yes. You can ask your agent to list your deployments or get details on a specific one, and it will pull the exact web endpoints and serving configurations for you.

How do I check my secrets with the Modal MCP?

You can ask your agent to list your secret dictionary references. It will show you what secrets are configured without you having to leave your chat interface.

Can this stop a runaway training job?

Absolutely. By using the stop_app capability, your agent can forcefully terminate a specific app execution by its ID to save on costs immediately.

Does the Modal MCP show my disk volumes?

Yes, it can list all your persisted disk network block volumes so you can verify which storage is attached to your distributed compute instances.

How do I see my app history with the Modal MCP?

You can ask your agent to list your apps. It will pull both active and historical app contexts, giving you a clear view of your previous and current executions.

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.

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.

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.

One connection away

Give your agent a direct line to Modal.

Connect Modal once. Keep it beside 5,900+ managed Connectors when the next task needs more.

Explore every Connector No credit card required · Free tier available

Modal for On-Demand GPU Infrastructure Management

You get instant, conversational control over your on-demand GPU infrastructure.

Stopping a stuck training job

Finding new inference endpoints

Verifying storage mounts

List apps

Stop app

List secrets

List volumes

List deployments

Get deployment

Get app

Open Connectors

Add the URL

Turn it on in chat

Open MCP settings

Add the URL

Save and start

Open MCP Settings

Add the server config

Save the file

Start using Modal (Serverless AI Infrastructure)

Create MCP config

Add the server config

Enable Agent mode

Start using Modal (Serverless AI Infrastructure)

Open MCP Settings

Add the server

Save and reload

Start using Modal (Serverless AI Infrastructure)

Open Cline MCP Settings

Add remote server

Enable the server

Start using Modal (Serverless AI Infrastructure)

Install Claude Code

Add the Connector

Verify the connection

Start using Modal (Serverless AI Infrastructure)

AI Engineer

Data Scientist

DevOps Engineer

RunPod

Lambda Labs (GPU Cloud)

Flystack

Paperspace

Render

Flightcontrol (AWS PaaS Deployments)

Give your agent a direct line to Modal.