DevRay DataLab MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@DevRay DataLab MCP inspect sample_classification.csv and summarize missing values"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
DevRay DataLab MCP
Local-first Data Science & Machine Learning for AI Assistants
DevRay DataLab MCP is a local-first Model Context Protocol (MCP) server that lets AI assistants such as Claude, Cursor, Cline, and Kilo Code perform real data science and machine learning on your own computer — no cloud services, no API keys, no paid subscriptions.
Everything runs locally via stdio: dataset loading, exploratory data analysis, preprocessing, classification/regression training, model comparison, export, and prediction. Your datasets never leave your machine.
Installation
Method A — uvx (simplest, no virtualenv)
uvx devray-datalab-mcpRequires uv. Install uv if needed:
# Windows PowerShell
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"Method B — pip in a virtual environment
python -m venv .venv
.\.venv\Scripts\Activate.ps1
python -m pip install devray-datalab-mcp
devray-datalab-mcpLinux / macOS:
python3 -m venv .venv
source .venv/bin/activate
pip install devray-datalab-mcp
devray-datalab-mcpMethod C — from GitHub source
pip install git+https://github.com/rayklanderman/devray-datalab-mcp.git
devray-datalab-mcpA stdio MCP server waits for input from an MCP client. Launching
devray-datalab-mcpdirectly without a connected client will appear to do nothing — this is expected. Connect it through an MCP-compatible client (see client configuration below).
Configure where datasets and model artifacts live with environment variables:
Variable | Default | Meaning |
|
| Directory containing CSV datasets |
|
| Directory for saved model artifacts |
Related MCP server: Kaggle Dataset Analyst
MCP client configuration
Add the server to your MCP-compatible client. Replace C:\MLData with your own paths.
Kilo Code
{
"mcpServers": {
"devray-datalab": {
"command": "uvx",
"args": [
"--from",
"devray-datalab-mcp",
"devray-datalab-mcp"
],
"env": {
"DEVRAY_WORKSPACE_DIR": "C:\\MLData\\datasets",
"DEVRAY_ARTIFACTS_DIR": "C:\\MLData\\artifacts"
}
}
}
}Cline / Cursor / Claude Desktop
These clients use the same mcpServers JSON structure:
{
"mcpServers": {
"devray-datalab": {
"command": "devray-datalab-mcp",
"args": [],
"env": {
"DEVRAY_WORKSPACE_DIR": "C:\\MLData\\datasets",
"DEVRAY_ARTIFACTS_DIR": "C:\\MLData\\artifacts"
}
}
}
}VS Code / GitHub Copilot MCP
Add to your VS Code MCP settings (settings.json):
{
"mcp.servers": {
"devray-datalab": {
"command": "devray-datalab-mcp",
"args": [],
"env": {
"DEVRAY_WORKSPACE_DIR": "${workspaceFolder}/datasets",
"DEVRAY_ARTIFACTS_DIR": "${workspaceFolder}/artifacts"
}
}
}
}Available tools
Tool | What it does |
| List CSV datasets in the workspace |
| Load a CSV; report types, missing values, stats, preview |
| Pearson/Spearman correlations, strongest pairs |
| Missing values, duplicates, constants, outliers, recommendations |
| Define target + task type; fit preprocessing on train data only |
| Train a classification or regression model |
| Compare multiple algorithms; select best by metric |
| Save model with pipeline, metadata, and schema |
| Generate predictions from a saved local model |
| CPU, RAM, storage, GPU detection |
Quickstart workflow
Using the included sample_classification.csv (target purchased):
Inspect:
inspect_datasetwith{"name": "sample_classification.csv"}Data quality:
analyze_data_qualitywith{"name": "sample_classification.csv"}Correlations:
analyze_correlationswith{"name": "sample_classification.csv", "method": "pearson"}Train & compare:
compare_modelswith{"name": "sample_classification.csv", "target_column": "purchased", "task_type": "classification", "metric": "f1"}Export:
export_modelwith{"artifact_name": "churn_model", "name": "sample_classification.csv", "target_column": "purchased", "task_type": "classification", "model_name": "random_forest"}Predict:
predictwith{"artifact_name": "churn_model", "features": {"age": 40, "income": 80000, "credit_score": 720, "category": "electronics", "region": "east"}}
A full step-by-step tutorial with copy-ready prompts is available in docs/quickstart.md.
Links
Security and privacy
All processing is local; no data leaves your machine. File access is confined to the configured workspace/artifacts directories. Path traversal is blocked, file sizes and extensions are validated, and only artifacts created by this application are loaded for prediction. No cloud hosting, no paid AI APIs, no external downloads.
License
MIT License. See LICENSE.
Available Tools
10 toolsanalyze_correlationsC
Compute numerical correlations and strongest pairs.
Inputs: name (required), top_n, method.
analyze_data_qualityC
Report data-quality issues and recommendations.
Inputs: name (required).
compare_modelsC
Train and compare multiple models; select best by metric.
Inputs: name (required), task_type (required), target_column (required), cv, +4 more.
export_modelC
Save a trained model with preprocessing pipeline and metadata.
Inputs: artifact_name (required), name, stratify, task_type, +5 more.
inspect_datasetC
Inspect a CSV dataset (types, missing values, stats).
Inputs: name (required), max_rows.
list_datasetsB
List datasets in the configured workspace.
Inputs: no named parameters.
predictC
Generate predictions using a previously trained local model.
Inputs: features (required), artifact_name (required).
prepare_datasetC
Define target and task type; fit preprocessing on training data only.
Inputs: name (required), task_type (required), target_column (required), stratify, +2 more.
system_infoA
Detect local CPU, RAM, storage, and GPU resources.
Inputs: no named parameters.
train_baselineC
Train one baseline model and report evaluation metrics.
Inputs: name (required), task_type (required), model_name (required), target_column (required), +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Most tools map to distinct pipeline stages (inspect, correlate, quality, prepare, train, compare, export, predict). The only mild overlap is between train_baseline and compare_models, both of which train models, but the single-model vs multi-model distinction is stated in the descriptions.
Names consistently use a verb_noun or clear verb-first pattern (list_datasets, inspect_dataset, analyze_correlations, prepare_dataset, train_baseline, compare_models, export_model). Minor deviations are predict (bare verb) and system_info (noun phrase), but these are still readable and unsurprising.
Ten tools is well within the ideal range and each maps to a meaningful step in a data-science workflow. No tool feels redundant or gratuitous.
The surface covers discovery, inspection, analysis, preparation, training, comparison, export, and inference, which is strong lifecycle coverage. Minor gaps remain: no tool to list or delete exported/trained models, and no dataset creation/import, so predict requires the agent to already know a model path.
Maintenance
Related MCP Connectors
Train AutoML models on CSV files and run predictions from Claude and other MCP clients.
Open, inspect, filter, edit and convert xlsx and csv files from your AI chat. Processing is local.
Open, inspect, filter, edit and convert xlsx and csv files from your AI chat. Processing is local.
Use your own trained text and picture classification models from any AI assistant.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with local CSV and Parquet data files through natural language queries, facilitating tasks like summarizing datasets or retrieving specific information.4-
- FlicenseAqualityDmaintenanceEnables exploratory data analysis and machine learning on CSV datasets with tools for profiling, missing values, correlation, plotting, model training, and prediction.8-
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to perform data analysis on local datasets through natural language, orchestrating Python, R, SQL, Spark, Jupyter, Power BI, and Tableau engines for statistics, machine learning, dashboard generation, and batch processing.Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to analyze large CSV files locally by importing them into SQLite, profiling columns, and running read-only SQL queries without data leaving the machine.MIT