Bring Mlops
to OpenAI Agents SDK

Connect your Neptune.ai account to any AI agent and take full control of your machine learning experimentation, model versioning, and training telemetry through natural conversation.

What you can do

• Experiment Orchestration — List all managed ML projects and retrieve detailed metadata configurations tracking active runs and workspace boundaries directly from your agent
• Run Audit & Search — Discover specific training runs or historical experiment state checkpoints mapping deep ML parameter sets and performance bounds securely
• Attribute Inspection — Extract detailed telemetry capturing the exact variables, accuracy metrics, and loss curves logged during specific execution checkpoints natively
• Model Registry Management — List and retrieve trained tracking models promoted and logged explicitly, isolating stable versions from ephemeral experimentation runs
• Organizational Visibility — Enumerate accessible workspaces and projects to understand your ML research footprint and documentation distribution natively
• Credential Audit — Verify specific user identifies and availability details bound inherently against your active service account token securely
• Metadata Retrieval — Deep-dive into specific Project or Run IDs to retrieve precise JSON representations and chronological experimentation insights instantly

How it works

1. Subscribe to this server
2. Enter your Neptune.ai API Token
3. Start managing your ML experiments from Claude, Cursor, or any MCP-compatible client

Who is this for?

• Data Scientists — monitor training progress and verify model metrics through natural conversation without manual dashboard navigation
• ML Engineers — audit the model registry and verify experiment attributes directly from your workspace terminal
• AI Researchers — track production model versions and ensure consistent metadata logging across multiple ML projects efficiently