Integration

Modal integration

Modal is a serverless cloud platform for running ML workloads, data processing, and web applications. Deploy Python functions as scalable endpoints, run GPU workloads on demand, schedule jobs, and build data pipelines. Features instant cold starts, pay-per-use pricing, and seamless Python integration. Ideal for ML inference, training jobs, batch processing, and serverless backends.

Connect Modal How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Modal.Built from the 10 Modal tools below, on the connection you add once.

Common Modal use cases

audit scheduled jobs
pause for maintenance
poll async completion
store API credentials
manage storage volumes
inventory deployed apps
inspect app configuration
long-running computations
inventory available secrets
real-time function execution

What you can do with Modal

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

App, 3 operations

get_appGet appGETRetrieves detailed information about a Modal application including functions, config, and usage metrics.
list_appsList appsGETLists all Modal applications in your workspace. Returns app IDs, names, deployment status, and function counts.
stop_appStop appPOSTStops a running Modal application. Terminates all active functions and stops accepting new requests.

Function, 2 operations

invoke_functionInvoke functionPOSTInvokes a Modal function synchronously with provided arguments. Returns the function result in real-time.
spawn_functionSpawn functionPOSTSpawns a Modal function asynchronously. Returns a call ID immediately for later result retrieval.

Secret, 2 operations

create_secretCreate secretPOSTCreates an encrypted secret in Modal for secure credential storage. Attach to apps for environment variable injection.
list_secretsList secretsGETLists all secrets in your Modal workspace. Returns names and metadata without exposing values.

Call, 1 operation

get_call_resultGet call resultGETRetrieves the status and result of an async Modal function call. Returns status and output when complete.

Schedule, 1 operation

list_schedulesList schedulesGETLists all scheduled jobs in Modal. Returns schedule definitions, cron expressions, and next run times.

Volume, 1 operation

list_volumesList volumesGETLists all persistent volumes in Modal. Returns volume names, sizes, and usage information.

Use Modal from Claude Code, Cursor or Codex

Connect Modal in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Modal operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Modal

Create your workspace
Sign up free. Nothing to install.
Connect Modal once
Add your Modal connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Modal integration FAQ

What can you do with the Modal integration?

LiveContext exposes 10 operations on Modal, covering app, function, secret and call. Common uses include audit scheduled jobs, pause for maintenance and poll async completion.