Use MLflow with your AI.
Connect your account once and let the AI you already use work with it, without building another integration. Manage ML lifecycle via MLflow. track training runs, monitor metrics, and audit the model registry.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Complete set · 6 capabilities
The complete MLflow capability set.
These are the exact actions your AI can choose when you ask it to work with MLflow.
01-03
3 capabilities in this set.
Part of 6 available through MLflow.
- 01
Search registered models
Search the MLflow Global Model Registry
- 02
Search runs
Search exact Model Training Runs across specific Experiments
- 03
List artifacts
List static artifacts attached over a specific Run
04-06
3 capabilities in this set.
Part of 6 available through MLflow.
- 04
Search experiments
Search all MLflow registered Experiments explicitly
- 05
Get experiment
Get an explicit explicit MLflow Experiment by ID configuration
- 06
Get run
Get parameters and metrics mapping a specific atomic Run ID
Observed, not estimated
825ms average. Fast in production.
MLflow is checked daily against the live service.
- Fastest day
- 666ms
- Slowest day
- 1064ms
- 14-day trend
- Stable+2%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 6 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of MLflow, so you can see the experience inside your AI.
It does not authenticate your account with MLflow. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
MLflow Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_O0ZBpwFtJKVOQRXy98KSjGZvQNA27XEpDUDcFNyB/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — MLflow capabilities are ready to use.
{
"mcpServers": {
"mlflow-ml-lifecycle-management-mcp": {
"url": "https://edge.vinkius.com/vk_preview_O0ZBpwFtJKVOQRXy98KSjGZvQNA27XEpDUDcFNyB/mcp"
}
}
}- Claude
- ChatGPT
- Cursor
- VS Code
- Windsurf
- Claude Code
- JetBrains
- Cline
Step-by-step instructions for each client are in the guide. How to connect
FAQ
Questions MLflow owners ask.
- 01
Can I see the metrics for a specific training run through my agent?
Yes. Use the get_run capability with a specific Run ID. Your agent will retrieve the detailed telemetry logged during that training session, including scalars like accuracy, loss, or any custom performance metrics you've defined.
- 02
How do I check which models are ready for production in the registry?
The search_registered_models capability allows your agent to query the global model registry. You can identify models that have been explicitly promoted to production or staging environments, helping you track deployment states across your project.
- 03
Can my agent list the plots or model files saved in a specific run?
Absolutely. Use the list_artifacts capability with a specific Run ID. Your agent will report all physical storage boundaries, including stored model blobs (e.g., .pkl, .h5) and saved image plots, ensuring you can locate critical training artifacts instantly.
Explore
More in Friends
Comet ML AI Connector
Manage machine learning experiments via Comet — track model metrics, audit project workspaces, and inspect ML
ViewReplicate AI Connector
Run ML models via Replicate — generate images, text, audio and video from community models, track predictions
ViewRagas AI Connector
Equip your AI with Ragas to create datasets, run RAG evaluations, and track experiment metrics directly from y
ViewMetatext AI Connector
No-code NLP and AI model management via Metatext — run inference and manage datasets.
View
Suggestions
Hugging Face AI Connector
Access thousands of pre-trained AI models for NLP, vision, and audio tasks with the largest open-source machin
ViewReplicate AI Connector
Equip your AI to dynamically search, run, and monitor thousands of open-source machine learning models hosted
ViewReplicate AI Connector
Automate machine learning workflows via Replicate — run models, manage predictions, and search for AI assets d
ViewYepCode AI Connector
Run serverless code snippets in the cloud with a platform that lets you build integrations and automations in
View