Tools on MCP Toolbox for Databases

dataplex-check-data-quality

Mon, 01 Jan 0001 00:00:00 +0000

About

A dataplex-check-data-quality tool triggers a new Data Quality scan to evaluate rules (e.g. non-null, value range limits, custom SQL assertions) against table rows.

Since scan template creation is asynchronous, this tool returns an LRO name. You must poll dataplex-get-operation with this ID until it is done, extract the scanId, and poll dataplex-get-run-status with the scanId until the job is SUCCEEDED before calling dataplex-get-data-quality-results to fetch results.

Compatible Sources

This tool can be used with the following database sources:

dataplex-discover-metadata

Mon, 01 Jan 0001 00:00:00 +0000

About

A dataplex-discover-metadata tool triggers a new Data Discovery scan to automatically crawl GCS directories, infer schemas/partitions, and publish them as BigQuery tables.

Compatible Sources

This tool can be used with the following database sources:

dataplex-generate-data-insights

Mon, 01 Jan 0001 00:00:00 +0000

About

A dataplex-generate-data-insights tool triggers the creation and run of a Dataplex Data Insights scan on a BigQuery table.

Since the scan template creation is asynchronous, this tool returns a Long-Running Operation (LRO) resource name (format: projects/{project}/locations/{location}/operations/{operation_id}). To orchestrate this workflow, you must:

Capture the operation_id from this tool’s response.
Poll the dataplex-get-operation tool with this ID until done is true.
Extract the created scan ID (scanId) from the completed operation’s response.
Poll dataplex-get-run-status with the scanId until the job state is SUCCEEDED.
Call dataplex-get-data-insights with the scanId to fetch the final results.

Compatible Sources

This tool can be used with the following database sources:

dataplex-generate-data-profile

Mon, 01 Jan 0001 00:00:00 +0000

About

A dataplex-generate-data-profile tool triggers a new Data Profile scan to compute statistical profiles (min, max, mean, null ratios, distinct ratios, quantiles, etc.) on table columns.

Compatible Sources

This tool can be used with the following database sources:

dataplex-get-data-insights

Mon, 01 Jan 0001 00:00:00 +0000

About

A dataplex-get-data-insights tool retrieves the final results of a completed Data Insights scan.

WARNING: You must verify that the execution run has succeeded (via dataplex-get-run-status) before calling this tool, otherwise the results will be empty. CRITICAL: Access the results only via the nested public GA fields dataDocumentationResult.datasetResult (for datasets) or dataDocumentationResult.tableResult (for tables). The top-level fields (like dataDocumentationResult.queries) are restricted and will be empty.

Compatible Sources

This tool can be used with the following database sources:

dataplex-get-data-profile

Mon, 01 Jan 0001 00:00:00 +0000

About

A dataplex-get-data-profile tool retrieves the results of a completed Data Profile scan.

WARNING: You must verify the execution run has succeeded (via dataplex-get-run-status) before calling this tool, otherwise the results will be empty. CRITICAL: Access the results via the nested public fields dataProfileResult.profile.fields inside the returned DataScan.

Compatible Sources

This tool can be used with the following database sources:

Source Name
Knowledge Catalog (formerly known as Dataplex) Source

Requirements

IAM Permissions

Knowledge Catalog uses Identity and Access Management (IAM) to control user and group access to Knowledge Catalog resources. Toolbox will use your Application Default Credentials (ADC) to authorize and authenticate when interacting with [Knowledge Catalog][dataplex-docs].

dataplex-get-data-quality-results

Mon, 01 Jan 0001 00:00:00 +0000

About

A dataplex-get-data-quality-results tool retrieves the results of a completed Data Quality scan.

WARNING: You must verify the execution run has succeeded (via dataplex-get-run-status) before calling this tool, otherwise the results will be empty. CRITICAL: Access the results via the nested public fields dataQualityResult inside the returned DataScan. Note that the failingRowsQuery field inside the rules result is extremely useful for retrieving failed rows.

Compatible Sources

This tool can be used with the following database sources:

dataplex-get-discovery-results

Mon, 01 Jan 0001 00:00:00 +0000

About

A dataplex-get-discovery-results tool retrieves the results of a completed Data Discovery scan.

WARNING: You must verify the execution run has succeeded (via dataplex-get-run-status) before calling this tool, otherwise the results will be empty. CRITICAL: Access the results via the nested public fields dataDiscoveryResult.bigqueryPublishing and dataDiscoveryResult.scanStatistics inside the returned DataScan.

Compatible Sources

This tool can be used with the following database sources:

Source Name
Knowledge Catalog (formerly known as Dataplex) Source

Requirements

IAM Permissions

dataplex-get-operation

Mon, 01 Jan 0001 00:00:00 +0000

About

A dataplex-get-operation tool retrieves the status of a Dataplex long-running operation (LRO) like scan creation.

Poll this tool until the done field from the response is true. Once completed, the response field will contain the created DataScan resource, from which you can extract the scanId (the last part of the name field, e.g. nq-doc-1234) to pass to get_run_status and get results. WARNING: This only tracks the creation of the scan template, NOT the actual background execution.

dataplex-get-run-status

Mon, 01 Jan 0001 00:00:00 +0000

About

A dataplex-get-run-status tool retrieves the execution status of the latest background job run for a specified scan.

Use this tool to poll the progress of the insights, profiling, discovery, or quality scan execution. Wait until the returned state is SUCCEEDED before fetching results. Typical execution takes 2-5 minutes. If the state is FAILED, check the error details.

Compatible Sources

This tool can be used with the following database sources:

dataplex-list-data-products

Mon, 01 Jan 0001 00:00:00 +0000

About

A dataplex-list-data-products tool lists all Data Products in Knowledge Catalog (formerly known as Dataplex) across all locations (globally).

View the Data Products usage guide for more information.

Compatible Sources

This tool can be used with the following database sources:

Source Name
Knowledge Catalog (formerly known as Dataplex) Source

Requirements

IAM Permissions

dataplex-lookup-context

Mon, 01 Jan 0001 00:00:00 +0000

About

A dataplex-lookup-context tool provides rich metadata of one or more data assets along with their relationships.

dataplex-lookup-context takes a required resources parameter which is a list of up to 10 resource names for which metadata is needed in the following form: projects/{project}/locations/{location}/entryGroups/{group}/entries/{entry}. All resources must belong to the same Google Cloud location.

Compatible Sources

This tool can be used with the following database sources:

Source Name
Knowledge Catalog (formerly known as Dataplex) Source

Requirements

IAM Permissions

Knowledge Catalog (formerly known as Dataplex) uses Identity and Access Management (IAM) to control user and group access to Knowledge Catalog resources. Toolbox will use your Application Default Credentials (ADC) to authorize and authenticate when interacting with Knowledge Catalog.

dataplex-lookup-entry

Mon, 01 Jan 0001 00:00:00 +0000

About

A dataplex-lookup-entry tool returns details of a particular entry in Knowledge Catalog.

Compatible Sources

This tool can be used with the following database sources:

Source Name
Knowledge Catalog (formerly known as Dataplex) Source

Requirements

IAM Permissions

dataplex-search-aspect-types

Mon, 01 Jan 0001 00:00:00 +0000

About

A dataplex-search-aspect-types tool allows to fetch the metadata template of aspect types based on search query.

Compatible Sources

This tool can be used with the following database sources:

Source Name
Knowledge Catalog (formerly known as Dataplex) Source

Requirements

IAM Permissions

dataplex-search-dq-scans

Mon, 01 Jan 0001 00:00:00 +0000

About

A dataplex-search-dq-scans tool returns data quality scans that match the given criteria.

Compatible Sources

This tool can be used with the following database sources:

Source Name
Knowledge Catalog (formerly known as Dataplex) Source

Requirements

IAM Permissions

Dataplex uses Identity and Access Management (IAM) to control user and group access to Dataplex resources. Toolbox will use your Application Default Credentials (ADC) to authorize and authenticate when interacting with Dataplex.

In addition to setting the ADC for your server, you need to ensure the IAM identity has been given the correct IAM permissions for the tasks you intend to perform. See Dataplex Universal Catalog IAM permissions and Dataplex Universal Catalog IAM roles for more information on applying IAM permissions and roles to an identity.

dataplex-search-entries

Mon, 01 Jan 0001 00:00:00 +0000

About

A dataplex-search-entries tool returns all entries in Knowledge Catalog (formerly known as Dataplex) (e.g. tables, views, models) that matches given user query.

Compatible Sources

This tool can be used with the following database sources:

Source Name
Knowledge Catalog (formerly known as Dataplex) Source