# Weights & Biases — how to use (mcp.ai)

Connect your Weights & Biases account and use 10 tools for developer tools straight from your AI agent. Connect with your own API key. Read W&B Models projects, runs, sweeps, artifact types, reports, automations, integrations, teams, and organizations through the W&B Cloud GraphQL API.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_weights_and_biases?ms=1787293620000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `weights_and_biases_get_current_viewer`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/weights_and_biases`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/weights_and_biases/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/weights_and_biases/get/current/viewer` — Return the authenticated W&B user, default entity, and team names for connection context.
- `POST https://api.mcp.ai/api/weights_and_biases/get/organization` — Return a W&B organization's identifiers and organization entity by exact name.
  - body: { organization_name: string }
- `POST https://api.mcp.ai/api/weights_and_biases/get/team` — Return a W&B team's identity and bounded membership metadata by exact team entity name.
  - body: { team_name: string }
- `POST https://api.mcp.ai/api/weights_and_biases/list/artifact/types` — Return one page of artifact types defined in a W&B project.
  - body: { cursor?: string, entity: string, project: string, per_page?: integer }
- `POST https://api.mcp.ai/api/weights_and_biases/list/automations` — Return one page of W&B automations accessible under an entity.
  - body: { cursor?: string, entity: string, per_page?: integer }
- `POST https://api.mcp.ai/api/weights_and_biases/list/integrations` — List one page of Slack workspace/channel metadata and webhook integration names for a W&B entity. Webhook URLs and credentials are excluded.
  - body: { cursor?: string, entity: string, per_page?: integer }
- `POST https://api.mcp.ai/api/weights_and_biases/list/projects` — Return one page of W&B projects visible under an entity.
  - body: { cursor?: string, entity: string, per_page?: integer }
- `POST https://api.mcp.ai/api/weights_and_biases/list/reports` — Return one page of beta W&B reports for a project.
  - body: { cursor?: string, entity: string, project: string, per_page?: integer }
- `POST https://api.mcp.ai/api/weights_and_biases/list/runs` — List one page of runs with IDs, display names, states, and creation times. Does not return run config, metrics, or history.
  - body: { cursor?: string, entity: string, project: string, per_page?: integer }
- `POST https://api.mcp.ai/api/weights_and_biases/list/sweeps` — Return one page of hyperparameter sweeps from a W&B project when sweeps are enabled for the account.
  - body: { cursor?: string, entity: string, project: string, per_page?: integer }

## Example prompts
- "What can I do in Weights & Biases?"
- "Show me a summary of my Weights & Biases account"

## More
- Page: https://mcp.ai/weights_and_biases
- Agent spec (llms.txt): https://mcp.ai/weights_and_biases/llms.txt
- Postman collection: https://mcp.ai/weights_and_biases/postman.json
