Modal (Serverless AI Infrastructure)

Modal (Serverless AI Infrastructure) MCP Connector for Claude

A+

Manage serverless compute via Modal — audit active apps, track GPU deployments, and monitor network volumes.

7 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your Modal account to any AI agent and take full control of your high-performance AI infrastructure, serverless GPU deployments, and persistent storage through natural conversation.

What you can do

  • App Orchestration — List isolated active and historical Modal app contexts to track function execution states and resource allocation directly from your agent
  • Deployment Management — Enumerate promoted long-running deployments and retrieve detailed web endpoints and serving configurations securely
  • Operational Control — Force stop actively running Modal app executions gracefully via App ID to prevent unnecessary billing cycles and manage system resources natively
  • Security & Secret Audit — List stored secret dictionary references and verify environment variable mappings attached to your serverless functions securely
  • Storage Visibility — Monitor persisted disk network block volumes and data mount directories used across your distributed compute instances
  • Infrastructure Inspection — Deep-dive into specific App or Deployment IDs to retrieve precise JSON metadata representing your infrastructure's current state vectors

How it works

  1. Subscribe to this server
  2. Enter your Modal Token ID and Token Secret
  3. Start managing your high-performance compute from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • AI Engineers — monitor GPU training jobs and verify deployment endpoints through natural conversation without manual CLI polling
  • Data Scientists — audit persistent volumes and check function execution logs directly from your workspace terminal
  • DevOps Teams — manage serverless secrets and track active app resource usage across multiple Modal projects efficiently
serverless-computegpu-deploymentinfrastructure-as-codecloud-scalingdistributed-computing

7 tools expose this connector's capabilities to your AI agent.

list_apps

List isolated active/historical Modal Apps contexts

get_app

Get static specifics of an exact Modal App ID

stop_app

Force stop an actively running explicit Modal App execution

list_secrets

List static secret dictionary configuration references

list_volumes

List Modal persisted disk network block volumes

list_deployments

List strictly managed Modal platform explicitly promoted deployments

get_deployment

Get an explicitly tracked deployment detail mapped bound

See how to talk to your AI agent using Modal (Serverless AI Infrastructure).

List all active Modal apps running in my account

I've retrieved your active Modal apps. Currently, 2 apps are running: 'gpu-trainer-alpha' (ID: ap-123, State: Running) and 'image-gen-service' (ID: ap-456, State: Initializing). Would you like to check the resource allocation for the GPU trainer?

Force stop Modal app ID 'ap-123'

Executing stop command… Success. Modal app 'ap-123' has been forcefully terminated. The serverless container has been spun down, and no further billing cycles will be triggered for this specific execution ID.

Show me all persistent volumes configured in my workspace

I've identified 3 persistent disk volumes: 'model-cache-v1' (Size: 50GB), 'training-datasets' (Size: 200GB), and 'user-data-store'. I can provide the mount paths for any of these volumes if you'd like.

Yes. Use the `stop_app` 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.

Related Connectors