Comet ML Connector for AI agents.
6 live capabilities
Track machine learning metrics and audit experiment parameters in real-time.
Waiting for input…
Why people use Comet ML
Comet ML for Auditing Machine Learning Experiment Metrics
With this Connector, you just ask your AI agent to find it. You can describe the project name or the goal, and it uses `list_projects` and `list_experiments` to pinpoint the exact data you need. You get the answer in seconds without ever opening a browser.
What Vinkius changes
You get a conversational interface for your entire machine learning experiment history.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Comparing model accuracies
A researcher wants to know which of 50 runs had the best accuracy.
- Real-world use case 02
Debugging a failed run
An engineer needs to see the parameters of a failed run.
- Real-world use case 03
Onboarding a new team member
A team lead wants to show a new dev where the 'NLP-v2' project lives.
Complete set · 6capabilities
The complete Comet ML capability set.
These are the exact actions your AI can choose when you ask it to work with Comet ML.
01—03
3 capabilities in this set.
Part of 6 available through Comet ML.
- 01 Capability
List workspaces
See all available routing spaces in your Comet ML account. This helps you find the right organizational area for your data.
- 02 Capability
List projects
Find specific projects within your designated Comet ML workspaces. Use this to see what research is currently active.
- 03 Capability
List experiments
Get a list of all logged experiments for a specific project. This is useful for seeing every training run you've conducted.
04—06
3 capabilities in this set.
Part of 6 available through Comet ML.
- 04 Capability
Get experiment
Fetch the specific details and logs for a unique experiment ID. Use it to see the full history of a single run.
- 05 Capability
Get experiment metrics
Pull the latest numeric metrics for a specific experiment run. This gives you the most recent accuracy and loss data.
- 06 Capability
Get experiment params
View the hyperparameters and configuration details of an experiment. Use this to verify your learning rates and model settings.
Set up in minutes
One URL. Then ask Comet ML to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Comet ML from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_C2PxqYqwffQi3V41WE8jlPynFSP048sA8SVR1PFT/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Comet ML, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Comet ML for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_C2PxqYqwffQi3V41WE8jlPynFSP048sA8SVR1PFT/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Comet ML URL.
- Step 03
Save and start
Save the connection and enable Comet ML in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"comet-ml": {
"url": "https://edge.vinkius.com/vk_preview_C2PxqYqwffQi3V41WE8jlPynFSP048sA8SVR1PFT/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Comet ML
Open Agent mode in chat and ask: "Using Comet ML, help me...". 6 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"comet-ml": {
"url": "https://edge.vinkius.com/vk_preview_C2PxqYqwffQi3V41WE8jlPynFSP048sA8SVR1PFT/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Comet ML
Ask Copilot: "Using Comet ML, help me...". 6 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"comet-ml": {
"url": "https://edge.vinkius.com/vk_preview_C2PxqYqwffQi3V41WE8jlPynFSP048sA8SVR1PFT/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Comet ML
Open Cascade and ask: "Using Comet ML, help me...". 6 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"comet-ml": {
"url": "https://edge.vinkius.com/vk_preview_C2PxqYqwffQi3V41WE8jlPynFSP048sA8SVR1PFT/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Comet ML
Ask Cline: "Using Comet ML, help me...". 6 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add comet-ml --transport http "https://edge.vinkius.com/vk_preview_C2PxqYqwffQi3V41WE8jlPynFSP048sA8SVR1PFT/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Comet ML
Ask Claude: "Using Comet ML, show me...". 6 tools are ready
Where the request belongs
Work Comet ML can move forward.
This is for the data science teams and ML engineers who are tired of manual dashboard navigation. If you spend your day auditing hundreds of training runs to find a single outlier, this capability puts that data in your chat.
Data Scientist
Uses the agent to quickly compare accuracy across dozens of different model versions during a research sprint.
ML Engineer
Verifies production hyperparameters and training configurations without leaving the code editor.
AI Researcher
Navigates through nested projects and workspaces to find specific historical data for peer review.
MLOps Engineer
Monitors active model evaluations and checks completion statuses in real-time to ensure pipeline health.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsNeptune.ai (ML Experiment Tracking)
Manage ML experiments via Neptune.ai. track training runs, monitor metrics, and audit model versions.
DVC
Manage ML experiments via DVC. track projects and views, audit experiments history, and monitor model runs directly from any AI agent.
MLflow (ML Lifecycle Management)
Manage ML lifecycle via MLflow. track training runs, monitor metrics, and audit the model registry.
Arize AI
Monitor ML model performance, detect data drift, and troubleshoot prediction quality with real-time observability dashboards.
Weights & Biases
Track experiments, monitor ML runs, and manage artifacts on WandB. the developer platform for AI.
DataRobot
Manage AutoML via DataRobot. monitor projects and models, track deployments, and audit ML datasets directly from any AI agent.
Bring your own AI
Change the model, client or framework. Keep Comet ML connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Comet ML.
The practical details behind the request, access and result.
Can the Comet ML MCP help me see my training metrics?
Yes, it lets your AI agent pull real-time accuracy, loss, and other numeric data from your Comet runs directly into your chat.
How do I find a specific project using Comet ML?
You can just ask your agent to list your projects or search for a specific one by name, and it will find the correct project ID for you.
Can I use this to check my hyperparameters?
Absolutely. You can ask the agent to retrieve the exact configuration for any specific experiment, including learning rates and batch sizes.
Does the Comet ML MCP work with my current AI client?
It works with any MCP-compatible client, including Claude, Cursor, and Windsurf.
Can I see all my workspaces at once?
Yes, the agent can list all your Comet workspaces to help you navigate different teams or projects quickly.
Is this for running my models?
No, this is for auditing and inspecting experiments you've already logged in Comet ML. It doesn't execute the training code itself.
Can my agent retrieve real-time metrics from an active ML run?
Yes. Use the 'get_experiment_metrics' capability with the experiment key. The agent will pull the latest numeric logged endpoints, allowing you to monitor loss, accuracy, and other custom metrics as they are generated.
How do I audit the parameters used in a specific experiment?
Provide the experiment key to your agent. The 'get_experiment_params' capability extracts all logged ML properties, helping you verify hyperparameters like learning rates, batch sizes, and model architectures.
Can I see a list of all experiments within a specific project?
Absolutely. Use the 'list_experiments' capability with the project ID. Your agent will surface all ML runs within that project, including their status and metadata, so you can quickly identify the results you need.
One connection away
Give your agent a direct line to Comet ML.
Connect Comet ML once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available