About DataSentinel
DataSentinel is an MCP server in the RAG category: dataSentinel is an autonomous agent-based pipeline that leverages the Model Context Protocol to securely automate data auditing and insight.
Install
git clone https://github.com/fahmymahamud/DataSentinelThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (7)
check_duplicatesFully duplicated rows, plus duplicate business keys if `key_columns` is given
Parameters not published.
check_missingNull % per column against warn / fail thresholds
Parameters not published.
check_outliersTukey IQR outliers on every numeric column
Parameters not published.
detect_piiRegex scan for emails, Singapore NRIC/FIN, SG mobile numbers, card numbers, plus suspicious column names. **Returns counts only — never the matched values**
Parameters not published.
profile_datasetRows, columns, dtypes, memory footprint
Parameters not published.
run_full_auditRuns everything above and returns a 0–100 score with a `PASS` / `WARN` / `FAIL` verdict
Parameters not published.
validate_schemaCompares columns and dtype families against an expected `{column: dtype}` map
Parameters not published.
Ask AI
Ask AI about DataSentinel
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.