- STATUS
- ENDPOINTS
- DETAILS
- HUMAN
Short answer
How can my AI track my Modal deployments?
Your agent uses Modal tools to list active deployments and fetch specific details like web endpoints for any service. You get a real-time view of your infrastructure directly in your chat. Here is the breakdown of what you can do.
Deployment outcomes.
Where your data lands.
Your AI pulls live data from your Modal account to give you these four views.
STATUS
Live deployment lists
The AI pulls a list of everything currently running. You see exactly what is active in your Modal account.
ENDPOINTS
Instant URL retrieval
The agent finds the specific web endpoints for your services. You get the exact URLs needed to hit your functions.
DETAILS
Deep service inspection
Your agent looks up specific deployment metadata. This gives you the granular info you need for a single service.
HUMAN
Manual code changes
The AI cannot modify your Modal code or change deployment settings. You still handle the actual deployment logic yourself.
The workflow
What your AI does when the deployment info arrives.
The agent acts as a bridge between your chat and the Modal infrastructure.
Inventory check
The agent scans your account to see what is currently deployed and running.
list_deploymentsTargeted lookup
Once you identify a specific service, the agent pulls its full configuration and status.
get_deploymentEndpoint extraction
The agent identifies the web endpoints associated with your active services.
get_deploymentStatus reporting
The agent summarizes the health and availability of your Modal services in plain text.
list_deploymentsget_deployment
Try it
Copy these to start.
Use these prompts to begin interacting with your Modal infrastructure.
Starting points
These are starting points. Swap out the deployment names for your actual Modal service identifiers.
Modal Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_yQfuiuyaifaMlCchZoeV6rYy4ok4PpgYEfzlMmar/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Modal capabilities are ready to use.
{
"mcpServers": {
"modal-serverless-ai-infrastructure-mcp": {
"url": "https://edge.vinkius.com/vk_preview_yQfuiuyaifaMlCchZoeV6rYy4ok4PpgYEfzlMmar/mcp"
}
}
}List all my current Modal deployments.
What is the web endpoint for my 'image-processor' deployment?
Check the status of the 'data-pipeline' service.
Show me all active deployments and their URLs.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Modal once, then ask.
One connection links your Modal account to your AI client. Your credentials stay encrypted and secure on our side.
Connect Modal to your AIFAQ
How this task behaves.
- 01
Can the AI deploy new Modal functions?
No. The AI can only list and retrieve information about existing deployments.
- 02
Can my agent change the configuration of a running service?
No. The tools only allow for reading deployment data, not modifying it.
- 03
How does the AI know which deployments are active?
It uses the list_deployments tool to fetch the current state of your Modal account.
- 04
Can I get the URL for a specific function?
Yes. The agent can retrieve web endpoints for your deployed services.
- 05
Does the AI need my Modal API key?
Yes, but you provide it through the secure Vinkius connection, and it stays encrypted.
More questions about Modal? The Connector page answers them. See everything the Modal Connector can do
Connect Modal to Claude, Cursor, ChatGPT & more
