Integration

Weights & Biases integration

MLOps platform for experiment tracking, model versioning, and collaboration. Build integrations for logging metrics, managing artifacts, comparing experiments, and automating ML workflows. Essential tool for machine learning teams.

Connect Weights & Biases How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Weights & Biases.Built from the 12 Weights & Biases tools below, on the connection you add once.

Common Weights & Biases use cases

List ML projects
Debug training runs
View model versions
Log training metrics
View team membership
Verify authentication
Version trained models
Download trained models
View experiment history
View experiment reports

What you can do with Weights & Biases

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.

Artifact, 3 operations

create_artifactCreate artifactPOSTCreates a new artifact for versioning.
get_artifactGet artifactPOSTRetrieves artifact details and file manifest.
list_artifactsList artifactsPOSTLists artifacts (models, datasets) in a project.

Run, 2 operations

get_runGet runPOSTRetrieves detailed information about a specific run.
list_runsList runsPOSTRetrieves runs (experiments) from a project.

Sweep, 2 operations

create_sweepCreate sweepPOSTCreates a new hyperparameter tuning sweep.
list_sweepsList sweepsPOSTLists hyperparameter tuning sweeps.

Metric, 1 operation

log_metricsLog metricsPOSTLogs metrics and data to a run.

Project, 1 operation

list_projectsList projectsPOSTRetrieves all projects for an entity.

Report, 1 operation

list_reportsList reportsPOSTLists collaborative reports.

Team, 1 operation

list_teamsList teamsPOSTLists teams the user is a member of.

User, 1 operation

get_userGet userPOSTRetrieves authenticated user profile.

Use Weights & Biases from Claude Code, Cursor or Codex

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

Create your workspace
Sign up free. Nothing to install.
Connect Weights & Biases once
Add your Weights & Biases 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.

Weights & Biases integration FAQ

What can you do with the Weights & Biases integration?

LiveContext exposes 12 operations on Weights & Biases, covering artifact, run, sweep and metric. Common uses include List ML projects, Debug training runs and View model versions.