What can you do with the Cerebrium integration?

LiveContext exposes 29 operations on Cerebrium, covering app, build, run and secret. Common uses include capacity planning, debug build failures and cost optimization.

LiveContext

All integrations

Cerebrium integration

Cerebrium is a serverless ML infrastructure platform for deploying and scaling machine learning models. Build custom inference pipelines, deploy pre-trained models, and run GPU workloads with automatic scaling and pay-per-second pricing. Supports PyTorch, TensorFlow, ONNX, and custom containers. Features include model chaining, streaming responses, async execution with webhooks, and built-in observability. Ideal for LLM applications, computer vision, generative AI, and real-time ML inference.

29 toolsTokenAPI docs

Connect Cerebrium How integrations work

Common Cerebrium use cases

capacity planning
debug build failures
cost optimization
add API keys
discover app IDs
video processing
view app secrets
abort slow builds
inventory secrets
inventory storage

What you can do with Cerebrium

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, 4 operations

DELETEdelete_app
Deletes a deployed Cerebrium app permanently.
GETget_app
Retrieves details of a specific Cerebrium app including configuration and metadata.
GETlist_apps
Lists all deployed apps in a Cerebrium project.
PATCHmodify_app
Updates Cerebrium app configuration including hardware, scaling, and concurrency settings.

Build, 4 operations

DELETEcancel_build
Cancels an in-progress Cerebrium build.
GETget_build
Retrieves details of a specific Cerebrium build.
GETget_build_logs
Retrieves build logs for a specific Cerebrium build.
GETlist_builds
Lists all builds for a Cerebrium app.

Run, 4 operations

DELETEcancel_run
Cancels an in-progress or queued Cerebrium run.
GETcount_queued_runs
Returns the queue depth (number of queued runs) for a Cerebrium app.
GETget_run
Retrieves status and details of a specific Cerebrium run. Returns status and outputs when complete.
GETlist_runs
Lists inference runs for a Cerebrium app. Returns run metadata with status and timing information.

Secret, 4 operations

GETlist_app_secrets
Lists all app-level secrets for a specific Cerebrium app.
GETlist_secrets
Lists all project-level secrets for a Cerebrium project.
PATCHupdate_app_secrets
Updates app-level secrets for a specific Cerebrium app.
PATCHupdate_secrets
Updates project-level secrets for a Cerebrium project.

Inference, 3 operations

POSTrun_async
Runs async inference on Cerebrium. Returns a run ID immediately for later result retrieval via webhook.
POSTrun_inference
Runs synchronous inference on a Cerebrium model. Sends inputs and receives predictions in real-time.
POSTrun_stream
Runs inference with streaming response on Cerebrium. Returns results incrementally via Server-Sent Events.

Container, 2 operations

GETlist_app_containers
Lists all currently active containers for a Cerebrium app.
DELETEstop_app_container
Stops a specific running container for a Cerebrium app.

Metric, 2 operations

GETget_app_dashboard_metrics
Retrieves dashboard metrics for a Cerebrium app.
GETget_app_resource_metrics
Retrieves resource utilization metrics (CPU, memory, GPU) for a Cerebrium app.

Project, 2 operations

GETget_project
Retrieves details of a specific Cerebrium project.
GETlist_projects
Lists all Cerebrium projects accessible to the authenticated user.

Volume, 2 operations

GETlist_volumes
Lists all persistent storage volumes for a Cerebrium project.
PATCHresize_volume
Resizes a persistent storage volume in a Cerebrium project.

Hardware, 1 operation

GETlist_hardware
Lists all available hardware options (GPU types) on the Cerebrium platform.

Log, 1 operation

GETget_app_logs
Retrieves logs for a Cerebrium app with optional date, container, and run filtering.

Use Cerebrium from Claude Code, Cursor or Codex

Connect Cerebrium in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Cerebrium 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 Cerebrium

Create your workspace
Sign up free. Nothing to install.
Connect Cerebrium once
Add your Cerebrium 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.

Cerebrium integration FAQ

What can you do with the Cerebrium integration?: LiveContext exposes 29 operations on Cerebrium, covering app, build, run and secret. Common uses include capacity planning, debug build failures and cost optimization.