data-quality-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATA_DIR | No | Directory containing CSV datasets. The server only reads files inside this directory; default is ./data relative to the working directory. | ./data |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Inspect CSV datasets in a single read-only data directory. Start with list_datasets, then use profile_dataset, find_issues and quality_score on a file name such as 'customers.csv'. suggest_cleaning only proposes steps; nothing is ever modified.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_datasetsA | List the CSV files in the data directory with their size and row count. |
| profile_datasetB | Profile a dataset: rows, columns, and per column the inferred type, missing %, unique count and example values. |
| find_issuesB | Find data quality issues (with severity and column): disguised missing values, sentinels like 999, >30% missing columns, constant columns, duplicate rows, IQR outliers and numbers stored as text. |
| quality_scoreB | Score a dataset 0-100 with a breakdown (completeness, uniqueness, validity, consistency) and a one-line explanation of how the score is computed. |
| preview_rowsB | Return the first n rows of a dataset exactly as stored (n is capped at 20). |
| suggest_cleaningB | Suggest concrete, ordered cleaning steps (with pandas code) based on find_issues. Suggestions only: no file is changed. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| audit_dataset | Profile, check and score a dataset, then decide if it is ready for training. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool targets a distinct output: file listing, structural profiling, issue detection, a single score, raw row preview, and cleaning recommendations. profile_dataset vs find_issues vs quality_score are related but clearly differentiated by what they return (stats vs issue list vs 0-100 score). No overlaps that would cause misselection.
Five tools follow a clean verb_noun pattern (profile_dataset, find_issues, preview_rows, suggest_cleaning, list_datasets). quality_score breaks the pattern with a noun_noun construction, a minor but visible deviation.
Six tools is well-scoped for a data quality analysis server, and each covers a distinct stage of the workflow. Nothing feels redundant or padded.
The read-only analysis lifecycle is well covered: discover, profile, detect issues, score, preview, and recommend fixes. The one gap is a way to apply or export the cleaning suggestions, so the workflow ends at recommendations rather than a fixable dataset.