Native V8 Connector for AI agents.
1 live capability
Get mathematically perfect ML metrics and model evaluation results.
Waiting for input…
Why people use Native V8
Stop AI Hallucinations in Machine Learning Evaluation with Confusion Matrix Engine
With the Confusion Matrix Engine MCP, you just hand the raw lists to your agent. It offloads the math to a local runtime and gives you the exact numbers in seconds. You skip the manual counting and get straight to the insights.
What Vinkius changes
You get 100% accurate metrics instead of AI guesses.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Detecting class bias in training sets
A data scientist has 500 test results and wants to know if the model is biased.
- Real-world use case 02
Debugging a classifier's failures
An ML engineer is debugging a classifier.
- Real-world use case 03
Generating metrics for a research paper
A researcher needs to report F1-Scores for a new paper.
Complete set · 1capability
The complete Native V8 capability set.
These are the exact actions your AI can choose when you ask it to work with Native V8.
01
1 capability in this set.
Part of 1 available through Native V8.
- 01 Capability
Calculate confusion matrix
Get the exact confusion matrix and accuracy from your actual and predicted label arrays. It handles the heavy lifting of counting matches and misses for you.
Set up in minutes
One URL. Then ask Native V8 to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Native V8 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_lcKPfQMdEs9vOL0QvMD7tp5xcmCCFVUKYwiOuwlI/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 Native V8, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Native V8 for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_lcKPfQMdEs9vOL0QvMD7tp5xcmCCFVUKYwiOuwlI/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 Native V8 URL.
- Step 03
Save and start
Save the connection and enable Native V8 in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"confusion-matrix-engine": {
"url": "https://edge.vinkius.com/vk_preview_lcKPfQMdEs9vOL0QvMD7tp5xcmCCFVUKYwiOuwlI/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 Native V8
Open Agent mode in chat and ask: "Using Native V8, help me...". 1 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"confusion-matrix-engine": {
"url": "https://edge.vinkius.com/vk_preview_lcKPfQMdEs9vOL0QvMD7tp5xcmCCFVUKYwiOuwlI/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 Native V8
Ask Copilot: "Using Native V8, help me...". 1 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"confusion-matrix-engine": {
"url": "https://edge.vinkius.com/vk_preview_lcKPfQMdEs9vOL0QvMD7tp5xcmCCFVUKYwiOuwlI/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 Native V8
Open Cascade and ask: "Using Native V8, help me...". 1 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"confusion-matrix-engine": {
"url": "https://edge.vinkius.com/vk_preview_lcKPfQMdEs9vOL0QvMD7tp5xcmCCFVUKYwiOuwlI/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 Native V8
Ask Cline: "Using Native V8, help me...". 1 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add confusion-matrix-engine --transport http "https://edge.vinkius.com/vk_preview_lcKPfQMdEs9vOL0QvMD7tp5xcmCCFVUKYwiOuwlI/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 Native V8
Ask Claude: "Using Native V8, show me...". 1 tools are ready
Where the request belongs
Work Native V8 can move forward.
Data scientists and ML engineers who need to validate model performance without manually building scripts or trusting LLM math.
ML Engineer
Validates production model performance during a deployment sprint to ensure no regressions.
Data Scientist
Quickly checks for class bias in a new training set without writing custom Python code.
AI Researcher
Evaluates experimental model outputs against ground truth to get publication-ready metrics.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsROC AUC Evaluator
Compute the exact Area Under the ROC Curve for binary classification predictions. Local, mathematically perfect, zero LLM estimation.
Arize AI
Monitor ML model performance, detect data drift, and troubleshoot prediction quality with real-time observability dashboards.
Braintrust
Automate AI evaluations with Braintrust. organize projects, test model datasets, run benchmarks, and manage prompts via any AI agent.
Nyckel ML
Classify data and perform semantic search via Nyckel. track ML functions, samples, and labels directly from your AI agent.
Zero-Shot vs Few-Shot Ratio Calculator
Analyze prompt structures to classify learning approaches and evaluate example density.
Abacus AI (Enterprise AI Cloud)
Manage the full machine learning lifecycle via Abacus AI. create projects, train models, and deploy real-time prediction endpoints.
Bring your own AI
Change the model, client or framework. Keep Native V8 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 Native V8.
The practical details behind the request, access and result.
Can the Confusion Matrix Engine MCP handle multi-class labels?
Yes, it works with any array of labels, whether you're doing binary classification or multiple categories.
Why shouldn't I just let the AI calculate the F1-Score?
LLMs are probabilistic, not deterministic. They often hallucinate decimals on large datasets, while this Connector uses a local runtime for perfect math.
Does the Confusion Matrix Engine MCP work with my local data?
Yes, it processes the arrays you provide to your agent locally, ensuring your data stays private and the math stays exact.
How does the Confusion Matrix Engine MCP help with model bias?
It generates a full breakdown of hits and misses, making it easy to see if the model is favoring one category over another.
What kind of metrics does the Confusion Matrix Engine MCP provide?
It calculates Accuracy, Precision, Recall, F1-Score, and the full confusion matrix breakdown.
Can I use the Confusion Matrix Engine MCP for any type of data?
It's designed for classification tasks where you have a list of actual results and a list of predicted results.
Why not let Claude/GPT calculate the accuracy?
LLMs operate on tokens and probability distributions. If you give them 500 predictions, they might summarize or estimate the F1-score rather than calculating it exactly. This engine ensures 100% mathematical precision.
Does it support multi-class classification?
Yes, the engine automatically detects unique labels from both arrays and constructs an N-by-N confusion matrix, handling both binary and multiclass evaluations flawlessly.
Is there a limit to the array size?
The only limit is the standard Context Window limit for transmitting the JSON arrays. For arrays exceeding 100k items, consider chunking or local CSV aggregators.
One connection away
Give your agent a direct line to Native V8.
Connect Native V8 once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available