DevRay DataLab MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEVRAY_ARTIFACTS_DIR | No | Directory for saved model artifacts. | artifacts |
| DEVRAY_WORKSPACE_DIR | No | Directory containing CSV datasets. | datasets |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
DevRay DataLab MCP is a local-first data science and machine learning server. All processing happens on your own computer. Use list_datasets, inspect_dataset, analyze_correlations, analyze_data_quality, prepare_dataset, train_baseline, compare_models, export_model, predict, and system_info.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_datasetsB | List datasets in the configured workspace. |
| inspect_datasetC | Inspect a CSV dataset (types, missing values, stats). |
| analyze_correlationsC | Compute numerical correlations and strongest pairs. |
| analyze_data_qualityC | Report data-quality issues and recommendations. |
| prepare_datasetC | Define target and task type; fit preprocessing on training data only. |
| train_baselineC | Train one baseline model and report evaluation metrics. |
| compare_modelsC | Train and compare multiple models; select best by metric. |
| export_modelC | Save a trained model with preprocessing pipeline and metadata. |
| predictC | Generate predictions using a previously trained local model. |
| system_infoA | Detect local CPU, RAM, storage, and GPU resources. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
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.