feat(dataplex): add tools to support metadata enrichment workflow by harmonisha-wq · Pull Request #3270 · googleapis/mcp-toolbox

harmonisha-wq · 2026-05-21T07:01:22Z

Description

Add the insights related tools for the enrich toolset in Dataplex.

PR Checklist

Thank you for opening a Pull Request! Before submitting your PR, there are a
few things you can do to make sure it goes smoothly:

Make sure you reviewed
CONTRIBUTING.md
Make sure to open an issue as a
bug/issue
before writing your code! That way we can discuss the change, evaluate
designs, and agree on the general idea
Ensure the tests and linter pass
Code coverage does not decrease (if any source code was changed)
Appropriate docs were updated (if necessary)
Make sure to add ! if this involve a breaking change

🛠️ Fixes #3269

gemini-code-assist

Code Review

This pull request introduces support for Dataplex Data Insights by adding four new tools: generate_data_insights, get_data_insights, get_operation, and get_run_status. These tools allow for asynchronous generation and retrieval of data documentation for BigQuery resources. The reviewer identified several performance and security improvements in the internal/sources/dataplex implementation, including the need for input validation on operation names to prevent path traversal, more efficient token management, and optimizing the retrieval of the latest scan job by using server-side ordering and pagination instead of client-side iteration.

Yuan325

Hi @harmonisha-wq thank you for adding these tools. Please also update (1) docs, and (2) integration tests for these tools. Thank you!

Yuan325

Hi, please see the following feedbacks on top of the comments:

Please update the prebuilt-config docs as well in docs/en/integrations/
Please apply the comments across all newly added tools.

This commit adds 6 new MCP tools to support Dataplex Data Profile, Data Discovery, and Data Quality workflows, completely integrated using standard gRPC client connections: - generate_data_profile / get_data_profile - generate_data_discovery / get_data_discovery - generate_data_quality / get_data_quality It also reuses get_operation and get_run_status to track these scans, and refactors GetDataInsights to a generic GetDataScan method. TAG=agy CONV=74c80935-9552-4038-b5b9-5c0d69b81a8d

…onfigBase This refactors the remaining 10 Dataplex write tools (checkdataquality, discovermetadata, generatedatainsights, generatedataprofile, getdatainsights, getdataprofile, getdataqualityresults, getdiscoveryresults, getoperation, getrunstatus) to match the new BaseTool framework design, and fixes the configuration initialization in their corresponding unit test files. TAG=agy CONV=74c80935-9552-4038-b5b9-5c0d69b81a8d

Yuan325

Thank you! :) PLease resolve the merge conflicts, I'll go ahead and merge it once ready

… tests

# Conflicts: # tests/dataplex/dataplex_integration_test.go

…nterface

…flow (#3270) ## Description > Add the insights related tools for the enrich toolset in Dataplex. ## PR Checklist > Thank you for opening a Pull Request! Before submitting your PR, there are a > few things you can do to make sure it goes smoothly: - [x] Make sure you reviewed [CONTRIBUTING.md](https://github.com/googleapis/mcp-toolbox/blob/main/CONTRIBUTING.md) - [x] Make sure to open an issue as a [bug/issue](https://github.com/googleapis/mcp-toolbox/issues/new/choose) before writing your code! That way we can discuss the change, evaluate designs, and agree on the general idea - [x] Ensure the tests and linter pass - [x] Code coverage does not decrease (if any source code was changed) - [ ] Appropriate docs were updated (if necessary) - [ ] Make sure to add `!` if this involve a breaking change 🛠️ Fixes #3269 --------- Co-authored-by: Yuan Teoh <[email protected]> Co-authored-by: Yuan Teoh <[email protected]> 05289aa

…flow (googleapis#3270) ## Description > Add the insights related tools for the enrich toolset in Dataplex. ## PR Checklist > Thank you for opening a Pull Request! Before submitting your PR, there are a > few things you can do to make sure it goes smoothly: - [x] Make sure you reviewed [CONTRIBUTING.md](https://github.com/googleapis/mcp-toolbox/blob/main/CONTRIBUTING.md) - [x] Make sure to open an issue as a [bug/issue](https://github.com/googleapis/mcp-toolbox/issues/new/choose) before writing your code! That way we can discuss the change, evaluate designs, and agree on the general idea - [x] Ensure the tests and linter pass - [x] Code coverage does not decrease (if any source code was changed) - [ ] Appropriate docs were updated (if necessary) - [ ] Make sure to add `!` if this involve a breaking change 🛠️ Fixes googleapis#3269 --------- Co-authored-by: Yuan Teoh <[email protected]> Co-authored-by: Yuan Teoh <[email protected]> 05289aa

🤖 I have created a release *beep* *boop* --- ## [1.5.0](v1.4.0...v1.5.0) (2026-06-18) ### Features * **auth/google:** Require audience or clientId for mcpEnabled ([#3450](#3450)) ([59f7b6e](59f7b6e)) * Enable per source level flags for sql commenter ([#3465](#3465)) ([ecce6b7](ecce6b7)) * **mcp:** Add URL parameter binding for HTTP transport ([#3112](#3112)) ([0cc7b37](0cc7b37)) * **scylladb:** Adding support for ScyllaDB source and tool ([#3119](#3119)) ([2dada83](2dada83)) * **server:** Add support for toolset filtering in prebuilt CLI flag ([#3245](#3245)) ([7cc4f65](7cc4f65)) * **skills:** Generate skills offline without live source connections ([#3388](#3388)) ([4c860b6](4c860b6)) * **skills:** Tolerate missing env vars during offline skills-generate ([#3399](#3399)) ([ea5d3e5](ea5d3e5)) * **source/cloud-storage:** Restrict bucket and local path access ([#3454](#3454)) ([2c3ca5d](2c3ca5d)) * **tools/bigquery:** Add per tool query label in BigQuery jobs ([#1975](#1975)) ([3f6a49f](3f6a49f)) * **tools/dataplex:** Add tools to support metadata enrichment workflow ([#3270](#3270)) ([05289aa](05289aa)) * **tools/mysql:** Add show-query-stats and list-all-locks tools for MySQL and Cloud SQL MySQL source ([#2954](#2954)) ([a9693bd](a9693bd)) * **tools:** Decouple tool initialization from sources ([#3355](#3355)) ([32a24e3](32a24e3)) ### Bug Fixes * **auth/dataplex:** Fix failing source with service account credentials ([#3369](#3369)) ([ba4deef](ba4deef)) * **bigquery:** Wire maximumBytesBilled into prebuilt config ([#3385](#3385)) ([4abbf6e](4abbf6e)) * Bound MCP HTTP body size ([#3216](#3216)) ([d4f4342](d4f4342)) * **config:** Add doc/line context to parse errors ([#2957](#2957)) ([4b097da](4b097da)) * Escape delimiter characters in applyEscape to prevent SQL injection ([#2811](#2811)) ([932519a](932519a)) * **npm:** Source binary version from cmd/version.txt ([#3417](#3417)) ([6ffbdec](6ffbdec)) * **prebuilt/alloydb-omni:** Require password env var explicitly ([#3398](#3398)) ([fcbe3e7](fcbe3e7)) * **server:** Fail if MCP auth is enabled together with enable-api ([#3435](#3435)) ([a6ff910](a6ff910)) * **server:** Return errors instead of panicking in InitializeConfigs ([#3397](#3397)) ([f48b01d](f48b01d)) * **source/cloudhealthcare:** Validate pageURL parameter to prevent SSRF ([#3453](#3453)) ([9abf47d](9abf47d)) * **source/dataplex,source/datalineage:** Specify cloud-platform scope for default credentials ([#3376](#3376)) ([13e8c36](13e8c36)) * **source/http:** Implement SSRF guard ([#3448](#3448)) ([24d7d29](24d7d29)) * **tool/bigquery-execute-sql:** Prevent dataset restriction bypass ([#3452](#3452)) ([ca6d5e3](ca6d5e3)) * **tool/mysql-get-query-plan:** Prevent query execution bypass and statement injection ([#3235](#3235)) ([7ed1e7b](7ed1e7b)) * **tool/spanner-sql,tool/spanner-execute-sql:** Use read-only annotations when readOnly is set ([#3338](#3338)) ([8bde0ec](8bde0ec)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). --------- Co-authored-by: release-please[bot] <55107282+release-please[bot]@users.noreply.github.com> Co-authored-by: Yuan Teoh <[email protected]>

🤖 I have created a release *beep* *boop* --- ## [1.5.0](v1.4.0...v1.5.0) (2026-06-18) ### Features * **auth/google:** Require audience or clientId for mcpEnabled ([#3450](#3450)) ([59f7b6e](59f7b6e)) * Enable per source level flags for sql commenter ([#3465](#3465)) ([ecce6b7](ecce6b7)) * **mcp:** Add URL parameter binding for HTTP transport ([#3112](#3112)) ([0cc7b37](0cc7b37)) * **scylladb:** Adding support for ScyllaDB source and tool ([#3119](#3119)) ([2dada83](2dada83)) * **server:** Add support for toolset filtering in prebuilt CLI flag ([#3245](#3245)) ([7cc4f65](7cc4f65)) * **skills:** Generate skills offline without live source connections ([#3388](#3388)) ([4c860b6](4c860b6)) * **skills:** Tolerate missing env vars during offline skills-generate ([#3399](#3399)) ([ea5d3e5](ea5d3e5)) * **source/cloud-storage:** Restrict bucket and local path access ([#3454](#3454)) ([2c3ca5d](2c3ca5d)) * **tools/bigquery:** Add per tool query label in BigQuery jobs ([#1975](#1975)) ([3f6a49f](3f6a49f)) * **tools/dataplex:** Add tools to support metadata enrichment workflow ([#3270](#3270)) ([05289aa](05289aa)) * **tools/mysql:** Add show-query-stats and list-all-locks tools for MySQL and Cloud SQL MySQL source ([#2954](#2954)) ([a9693bd](a9693bd)) * **tools:** Decouple tool initialization from sources ([#3355](#3355)) ([32a24e3](32a24e3)) ### Bug Fixes * **auth/dataplex:** Fix failing source with service account credentials ([#3369](#3369)) ([ba4deef](ba4deef)) * **bigquery:** Wire maximumBytesBilled into prebuilt config ([#3385](#3385)) ([4abbf6e](4abbf6e)) * Bound MCP HTTP body size ([#3216](#3216)) ([d4f4342](d4f4342)) * **config:** Add doc/line context to parse errors ([#2957](#2957)) ([4b097da](4b097da)) * Escape delimiter characters in applyEscape to prevent SQL injection ([#2811](#2811)) ([932519a](932519a)) * **npm:** Source binary version from cmd/version.txt ([#3417](#3417)) ([6ffbdec](6ffbdec)) * **prebuilt/alloydb-omni:** Require password env var explicitly ([#3398](#3398)) ([fcbe3e7](fcbe3e7)) * **server:** Fail if MCP auth is enabled together with enable-api ([#3435](#3435)) ([a6ff910](a6ff910)) * **server:** Return errors instead of panicking in InitializeConfigs ([#3397](#3397)) ([f48b01d](f48b01d)) * **source/cloudhealthcare:** Validate pageURL parameter to prevent SSRF ([#3453](#3453)) ([9abf47d](9abf47d)) * **source/dataplex,source/datalineage:** Specify cloud-platform scope for default credentials ([#3376](#3376)) ([13e8c36](13e8c36)) * **source/http:** Implement SSRF guard ([#3448](#3448)) ([24d7d29](24d7d29)) * **tool/bigquery-execute-sql:** Prevent dataset restriction bypass ([#3452](#3452)) ([ca6d5e3](ca6d5e3)) * **tool/mysql-get-query-plan:** Prevent query execution bypass and statement injection ([#3235](#3235)) ([7ed1e7b](7ed1e7b)) * **tool/spanner-sql,tool/spanner-execute-sql:** Use read-only annotations when readOnly is set ([#3338](#3338)) ([8bde0ec](8bde0ec)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). --------- Co-authored-by: release-please[bot] <55107282+release-please[bot]@users.noreply.github.com> Co-authored-by: Yuan Teoh <[email protected]> 45c0f86

🤖 I have created a release *beep* *boop* --- ## [1.5.0](googleapis/mcp-toolbox@v1.4.0...v1.5.0) (2026-06-18) ### Features * **auth/google:** Require audience or clientId for mcpEnabled ([googleapis#3450](googleapis#3450)) ([59f7b6e](googleapis@59f7b6e)) * Enable per source level flags for sql commenter ([googleapis#3465](googleapis#3465)) ([ecce6b7](googleapis@ecce6b7)) * **mcp:** Add URL parameter binding for HTTP transport ([googleapis#3112](googleapis#3112)) ([0cc7b37](googleapis@0cc7b37)) * **scylladb:** Adding support for ScyllaDB source and tool ([googleapis#3119](googleapis#3119)) ([2dada83](googleapis@2dada83)) * **server:** Add support for toolset filtering in prebuilt CLI flag ([googleapis#3245](googleapis#3245)) ([7cc4f65](googleapis@7cc4f65)) * **skills:** Generate skills offline without live source connections ([googleapis#3388](googleapis#3388)) ([4c860b6](googleapis@4c860b6)) * **skills:** Tolerate missing env vars during offline skills-generate ([googleapis#3399](googleapis#3399)) ([ea5d3e5](googleapis@ea5d3e5)) * **source/cloud-storage:** Restrict bucket and local path access ([googleapis#3454](googleapis#3454)) ([2c3ca5d](googleapis@2c3ca5d)) * **tools/bigquery:** Add per tool query label in BigQuery jobs ([googleapis#1975](googleapis#1975)) ([3f6a49f](googleapis@3f6a49f)) * **tools/dataplex:** Add tools to support metadata enrichment workflow ([googleapis#3270](googleapis#3270)) ([05289aa](googleapis@05289aa)) * **tools/mysql:** Add show-query-stats and list-all-locks tools for MySQL and Cloud SQL MySQL source ([googleapis#2954](googleapis#2954)) ([a9693bd](googleapis@a9693bd)) * **tools:** Decouple tool initialization from sources ([googleapis#3355](googleapis#3355)) ([32a24e3](googleapis@32a24e3)) ### Bug Fixes * **auth/dataplex:** Fix failing source with service account credentials ([googleapis#3369](googleapis#3369)) ([ba4deef](googleapis@ba4deef)) * **bigquery:** Wire maximumBytesBilled into prebuilt config ([googleapis#3385](googleapis#3385)) ([4abbf6e](googleapis@4abbf6e)) * Bound MCP HTTP body size ([googleapis#3216](googleapis#3216)) ([d4f4342](googleapis@d4f4342)) * **config:** Add doc/line context to parse errors ([googleapis#2957](googleapis#2957)) ([4b097da](googleapis@4b097da)) * Escape delimiter characters in applyEscape to prevent SQL injection ([googleapis#2811](googleapis#2811)) ([932519a](googleapis@932519a)) * **npm:** Source binary version from cmd/version.txt ([googleapis#3417](googleapis#3417)) ([6ffbdec](googleapis@6ffbdec)) * **prebuilt/alloydb-omni:** Require password env var explicitly ([googleapis#3398](googleapis#3398)) ([fcbe3e7](googleapis@fcbe3e7)) * **server:** Fail if MCP auth is enabled together with enable-api ([googleapis#3435](googleapis#3435)) ([a6ff910](googleapis@a6ff910)) * **server:** Return errors instead of panicking in InitializeConfigs ([googleapis#3397](googleapis#3397)) ([f48b01d](googleapis@f48b01d)) * **source/cloudhealthcare:** Validate pageURL parameter to prevent SSRF ([googleapis#3453](googleapis#3453)) ([9abf47d](googleapis@9abf47d)) * **source/dataplex,source/datalineage:** Specify cloud-platform scope for default credentials ([googleapis#3376](googleapis#3376)) ([13e8c36](googleapis@13e8c36)) * **source/http:** Implement SSRF guard ([googleapis#3448](googleapis#3448)) ([24d7d29](googleapis@24d7d29)) * **tool/bigquery-execute-sql:** Prevent dataset restriction bypass ([googleapis#3452](googleapis#3452)) ([ca6d5e3](googleapis@ca6d5e3)) * **tool/mysql-get-query-plan:** Prevent query execution bypass and statement injection ([googleapis#3235](googleapis#3235)) ([7ed1e7b](googleapis@7ed1e7b)) * **tool/spanner-sql,tool/spanner-execute-sql:** Use read-only annotations when readOnly is set ([googleapis#3338](googleapis#3338)) ([8bde0ec](googleapis@8bde0ec)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). --------- Co-authored-by: release-please[bot] <55107282+release-please[bot]@users.noreply.github.com> Co-authored-by: Yuan Teoh <[email protected]> 45c0f86

harmonisha-wq requested review from a team as code owners May 21, 2026 07:01

blunderbuss-gcf Bot assigned Yuan325 May 21, 2026

gemini-code-assist Bot reviewed May 21, 2026

View reviewed changes

harmonisha-wq force-pushed the feat/dataplex-enrichment branch 2 times, most recently from 83016d5 to 2e89480 Compare May 21, 2026 10:47

harmonisha-wq commented May 26, 2026

View reviewed changes

Comment thread internal/sources/dataplex/dataplex.go Outdated

harmonisha-wq force-pushed the feat/dataplex-enrichment branch 2 times, most recently from e3a91fa to ce3547a Compare May 27, 2026 05:36

sumedhdk22 reviewed May 27, 2026

View reviewed changes

Comment thread internal/prebuiltconfigs/tools/dataplex.yaml Outdated

sumedhdk22 reviewed May 27, 2026

View reviewed changes

Comment thread internal/prebuiltconfigs/tools/dataplex.yaml Outdated

sumedhdk22 reviewed May 27, 2026

View reviewed changes

Comment thread internal/prebuiltconfigs/tools/dataplex.yaml Outdated

sumedhdk22 reviewed May 27, 2026

View reviewed changes

Comment thread internal/prebuiltconfigs/tools/dataplex.yaml Outdated

Comment thread internal/prebuiltconfigs/tools/dataplex.yaml Outdated

Comment thread internal/prebuiltconfigs/tools/dataplex.yaml Outdated

Comment thread internal/prebuiltconfigs/tools/dataplex.yaml Outdated

harmonisha-wq force-pushed the feat/dataplex-enrichment branch 9 times, most recently from 776be3f to 651f2ce Compare June 1, 2026 04:26

sumedhdk22 approved these changes Jun 2, 2026

View reviewed changes

Comment thread internal/prebuiltconfigs/tools/dataplex.yaml Outdated

Comment thread internal/prebuiltconfigs/tools/dataplex.yaml

Comment thread internal/prebuiltconfigs/tools/dataplex.yaml Outdated

Yuan325 reviewed Jun 3, 2026

View reviewed changes

Comment thread internal/prebuiltconfigs/tools/dataplex.yaml Outdated

Yuan325 requested changes Jun 9, 2026

View reviewed changes

Yuan325 added the release candidate Use label to signal PR should be included in the next release. label Jun 9, 2026

harmonisha-wq force-pushed the feat/dataplex-enrichment branch 2 times, most recently from b2384ea to 37b6cb9 Compare June 11, 2026 08:44

harmonisha-wq added 2 commits June 11, 2026 08:50

feat(dataplex): add tools to support metadata enrichment workflow

70ebc47

harmonisha-wq force-pushed the feat/dataplex-enrichment branch 7 times, most recently from 8f56181 to c30a8db Compare June 11, 2026 16:11

anikasharma03 approved these changes Jun 12, 2026

View reviewed changes

Yuan325 approved these changes Jun 15, 2026

View reviewed changes

Comment thread internal/tools/dataplex/dataplexcommon/util_test.go

harmonisha-wq added 2 commits June 16, 2026 07:32

Fix dataplex search dq scans parameters and update unit & integration…

a34f492

… tests

Merge remote-tracking branch 'origin/main' into pr-3270

83acc9e

# Conflicts: # tests/dataplex/dataplex_integration_test.go

harmonisha-wq force-pushed the feat/dataplex-enrichment branch from 9ac90ab to 83acc9e Compare June 16, 2026 08:04

harmonisha-wq and others added 2 commits June 16, 2026 09:02

fix(dataplex): update Initialize signature to match new mcp-toolbox i…

4c7f25a

…nterface

Merge branch 'main' into feat/dataplex-enrichment

5393b3c

Yuan325 enabled auto-merge (squash) June 17, 2026 01:23

Yuan325 force-pushed the feat/dataplex-enrichment branch from 9a33dcc to 0bf6670 Compare June 17, 2026 01:25

fix docs lint

a01448b

Yuan325 force-pushed the feat/dataplex-enrichment branch from 0bf6670 to a01448b Compare June 17, 2026 01:28

Yuan325 merged commit 05289aa into googleapis:main Jun 17, 2026
27 checks passed

release-please Bot mentioned this pull request Jun 16, 2026

chore(main): release 1.5.0 #3379

Merged

BrewTestBot mentioned this pull request Jun 18, 2026

mcp-toolbox 1.5.0 Homebrew/homebrew-core#288736

Merged

Uh oh!

Conversation

harmonisha-wq commented May 21, 2026

Description

PR Checklist

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Yuan325 left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Yuan325 left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Yuan325 left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Yuan325 left a comment •

edited

Loading