feat(serverless-spark): add list/get sessions commands by dborowitz · Pull Request #2576 · googleapis/mcp-toolbox

dborowitz · 2026-02-27T17:48:33Z

Description

Adds commands for Serverless Spark sessions analogous to existing list/get commands for batches.

Unlike batches, we don't plan to add create session commands, as these are generally only created via the Jupyter protocol. Agents will need to have other ways to create sessions, for example by interacting directly with an IDE like Jupyter Lab or VS Code, but those won't be part of MCP Toolbox.

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

🛠️ Part of #2405

gemini-code-assist · 2026-02-27T17:49:01Z

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly enhances the Serverless Spark integration by introducing capabilities to list and retrieve Spark sessions. These new tools provide users with greater visibility and control over their interactive Spark environments, aligning session management with the existing batch management features. The changes involve adding new API clients, implementing core logic for session operations, and updating all relevant configurations and documentation to support these new functionalities.

Highlights

New Serverless Spark Session Tools: Introduced list_sessions and get_session tools for managing Serverless Spark sessions, mirroring existing functionality for batches.
Core Logic Implementation: Added the underlying Go logic within the serverlessspark source to handle listing and retrieving Spark sessions, including client initialization, data structures, and URL generation for console and logs.
Tool Configuration and Integration: Configured the new session tools in serverless-spark.yaml and integrated them into the serverless_spark_tools toolset, making them discoverable and usable.
Documentation Updates: Updated the reference documentation and tool resource pages to include details, examples, and parameters for the new list_sessions and get_session tools.
Comprehensive Testing: Added unit tests for the new session URL utilities and tool configurations, along with integration tests covering success, error handling, and authentication for both list-sessions and get-session endpoints.

Changelog

cmd/internal/imports.go
- Added imports for serverlesssparkgetsession and serverlesssparklistsessions packages.
cmd/internal/tools_file_test.go
- Updated the serverless_spark_tools toolset configuration to include list_sessions and get_session.
docs/en/reference/prebuilt-tools.md
- Added documentation entries for list_sessions and get_session tools under Serverless Spark.
docs/en/resources/sources/serverless-spark.md
- Added links to the new serverless-spark-list-sessions.md and serverless-spark-get-session.md documentation.
docs/en/resources/tools/serverless-spark/_index.md
- Included new markdown files for serverless-spark-get-session and serverless-spark-list-sessions in the index.
docs/en/resources/tools/serverless-spark/serverless-spark-get-session.md
- Added new documentation file detailing the serverless-spark-get-session tool, its parameters, and response format.
docs/en/resources/tools/serverless-spark/serverless-spark-list-sessions.md
- Added new documentation file detailing the serverless-spark-list-sessions tool, its parameters, and response format.
internal/prebuiltconfigs/tools/serverless-spark.yaml
- Configured new list_sessions and get_session tools with their respective kinds and sources.
- Added list_sessions and get_session to the serverless_spark_tools toolset.
internal/sources/serverlessspark/serverlessspark.go
- Imported the errors package.
- Initialized a new SessionControllerClient during source configuration.
- Added a SessionClient field to the Source struct.
- Implemented GetSessionControllerClient method to return the session client.
- Updated the Close method to close the SessionClient in addition to existing clients.
- Implemented ListSessions function to retrieve and format a list of Spark sessions.
- Implemented GetSession function to retrieve and format a specific Spark session.
- Added ToSessions helper function to convert protobuf session messages to custom Session structs.
internal/sources/serverlessspark/url.go
- Added sessionFullNameRegex for parsing session names.
- Implemented ExtractSessionDetails to extract project ID, location, and session ID from a session name.
- Implemented SessionConsoleURL to generate a Google Cloud Console URL for a session summary.
- Implemented SessionLogsURL to generate a Google Cloud Console URL for session logs with filtering.
- Implemented SessionConsoleURLFromProto and SessionLogsURLFromProto to generate URLs from protobuf session objects.
internal/sources/serverlessspark/url_test.go
- Added unit tests for ExtractSessionDetails covering success and failure cases.
- Added unit tests for SessionConsoleURL and SessionLogsURL.
- Added unit tests for SessionConsoleURLFromProto and SessionLogsURLFromProto.
- Added a test case for URL escaping in SessionLogsURL.
internal/tools/serverlessspark/serverlesssparkgetsession/serverlesssparkgetsession.go
- Added new Go tool implementation for serverless-spark-get-session, including configuration, initialization, and invocation logic.
internal/tools/serverlessspark/serverlesssparkgetsession/serverlesssparkgetsession_test.go
- Added unit tests for parsing serverless-spark-get-session tool configuration from YAML.
internal/tools/serverlessspark/serverlesssparklistsessions/serverlesssparklistsessions.go
- Added new Go tool implementation for serverless-spark-list-sessions, including configuration, initialization, and invocation logic.
internal/tools/serverlessspark/serverlesssparklistsessions/serverlesssparklistsessions_test.go
- Added unit tests for parsing serverless-spark-list-sessions tool configuration from YAML.
tests/serverlessspark/serverless_spark_integration_test.go
- Added list-sessions and list-sessions-with-auth tool configurations for integration tests.
- Added get-session and get-session-with-auth tool configurations for integration tests.
- Initialized a new dataproc.SessionControllerClient for integration tests.
- Added integration tests for list-sessions covering success, error cases (zero/negative page size), and authentication.
- Added integration tests for get-session covering success (using an existing session), error cases (missing session, full session name), and authentication.
- Implemented runListSessionsTest and listSessionsRpc helper functions for listing sessions in tests.
- Implemented runGetSessionTest helper function for getting sessions in tests.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	`/gemini review`	Performs a code review for the current pull request in its current state.
Pull Request Summary	`/gemini summary`	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	`/gemini help`	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

gemini-code-assist

Code Review

This pull request adds list and get commands for Serverless Spark sessions, analogous to the existing batch commands. The changes are well-implemented, including new tool definitions, source modifications for session clients, URL generation logic, and integration tests. The documentation has also been updated. My review identifies a few minor issues: the example console URLs in the new documentation are incorrect, and there's a small logic inconsistency in a test helper function that could be improved.

github-actions · 2026-02-27T18:36:25Z

🔎 Preview at https://googleapis.github.io/genai-toolbox/previews/PR-2576/

dborowitz · 2026-02-27T18:42:27Z

Integration test failure in serverless-spark is an unrelated flake. (I think we're generally less flaky than some other tests, but if it turns into an issue we can increase the relevant timeout)

duwenxin99 · 2026-03-03T18:17:39Z

/gcbrun

## Description Adds commands for Serverless Spark sessions analogous to existing list/get commands for batches. Unlike batches, we don't plan to add create session commands, as these are generally only created via the Jupyter protocol. Agents will need to have other ways to create sessions, for example by interacting directly with an IDE like Jupyter Lab or VS Code, but those won't be part of MCP Toolbox. ## 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](https://github.com/googleapis/genai-toolbox/blob/main/CONTRIBUTING.md) - [ ] Make sure to open an issue as a [bug/issue](https://github.com/googleapis/genai-toolbox/issues/new/choose) 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 🛠️ Part of #2405 Co-authored-by: Wenxin Du <117315983+duwenxin99@users.noreply.github.com> a554298

…eapis#2576) ## Description Adds commands for Serverless Spark sessions analogous to existing list/get commands for batches. Unlike batches, we don't plan to add create session commands, as these are generally only created via the Jupyter protocol. Agents will need to have other ways to create sessions, for example by interacting directly with an IDE like Jupyter Lab or VS Code, but those won't be part of MCP Toolbox. ## 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](https://github.com/googleapis/genai-toolbox/blob/main/CONTRIBUTING.md) - [ ] Make sure to open an issue as a [bug/issue](https://github.com/googleapis/genai-toolbox/issues/new/choose) 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 🛠️ Part of googleapis#2405 Co-authored-by: Wenxin Du <117315983+duwenxin99@users.noreply.github.com> a554298

## Description Adds commands for Serverless Spark sessions analogous to existing list/get commands for batches. Unlike batches, we don't plan to add create session commands, as these are generally only created via the Jupyter protocol. Agents will need to have other ways to create sessions, for example by interacting directly with an IDE like Jupyter Lab or VS Code, but those won't be part of MCP Toolbox. ## 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](https://github.com/googleapis/genai-toolbox/blob/main/CONTRIBUTING.md) - [ ] Make sure to open an issue as a [bug/issue](https://github.com/googleapis/genai-toolbox/issues/new/choose) 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 🛠️ Part of #2405 Co-authored-by: Wenxin Du <117315983+duwenxin99@users.noreply.github.com>

…eapis#2576) ## Description Adds commands for Serverless Spark sessions analogous to existing list/get commands for batches. Unlike batches, we don't plan to add create session commands, as these are generally only created via the Jupyter protocol. Agents will need to have other ways to create sessions, for example by interacting directly with an IDE like Jupyter Lab or VS Code, but those won't be part of MCP Toolbox. ## 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](https://github.com/googleapis/genai-toolbox/blob/main/CONTRIBUTING.md) - [ ] Make sure to open an issue as a [bug/issue](https://github.com/googleapis/genai-toolbox/issues/new/choose) 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 🛠️ Part of googleapis#2405 Co-authored-by: Wenxin Du <117315983+duwenxin99@users.noreply.github.com> a554298

🤖 I have created a release *beep* *boop* --- ## [0.29.0](v0.28.0...v0.29.0) (2026-03-13) ### ⚠ BREAKING CHANGES * **source/alloydb:** restructure prebuilt toolsets ([#2639](#2639)) * **source/spanner:** restructure prebuilt toolsets ([#2641](#2641)) * **source/dataplex:** restructure prebuilt toolsets ([#2640](#2640)) * **source/oss-db:** restructure prebuilt toolsets ([#2638](#2638)) * **source/cloudsql:** restructure prebuilt toolsets ([#2635](#2635)) * **source/bigquery:** restructure prebuilt toolsets ([#2637](#2637)) * **source/firestore:** restructure prebuilt toolsets ([#2636](#2636)) * telemetry metrics updates as per semantic convention ([#2566](#2566)) ### Features * Add user agent to embeddings generation ([#2572](#2572)) ([287251a](287251a)) * **skill:** Attach user agent metadata for generated skill ([#2697](#2697)) ([9598a6a](9598a6a)) * **skills:** Add additional-notes flag to generate skills command ([#2696](#2696)) ([73bf962](73bf962)) * **skill:** Update skill generation logic ([#2646](#2646)) ([c233eee](c233eee)) * **source/alloydb:** Restructure prebuilt toolsets ([#2639](#2639)) ([5f3f063](5f3f063)) * **source/bigquery:** Restructure prebuilt toolsets ([#2637](#2637)) ([dc984ba](dc984ba)) * **sources/bigquery:** Support custom oauth header name ([#2564](#2564)) ([d3baf77](d3baf77)) * **source/cloudsql:** Restructure prebuilt toolsets ([#2635](#2635)) ([99613dc](99613dc)) * **source/dataplex:** Restructure prebuilt toolsets ([#2640](#2640)) ([acb9a80](acb9a80)) * **source/firestore:** Restructure prebuilt toolsets ([#2636](#2636)) ([22ab7b9](22ab7b9)) * **source/oss-db:** Restructure prebuilt toolsets ([#2638](#2638)) ([5196c6a](5196c6a)) * **source/spanner:** Restructure prebuilt toolsets ([#2641](#2641)) ([ea2b698](ea2b698)) * Telemetry metrics updates as per semantic convention ([#2566](#2566)) ([131d764](131d764)) * **tools/mongodb:** Add tool annotations to MongoDB tools for improved LLM understanding ([#2219](#2219)) ([b7a5f80](b7a5f80)) * **tools/serverless-spark:** Add get_session_template tool ([#2308](#2308)) ([a136e16](a136e16)) * **tools/serverless-spark:** Add list/get sessions tools ([#2576](#2576)) ([a554298](a554298)) ### Bug Fixes * Improve list locks integration test for postgres ([#2279](#2279)) ([d9ebe5d](d9ebe5d)) * **mcp:** Guard nil SSE session lookup and return 400 for missing session ([#2681](#2681)) ([f66189f](f66189f)) * **oracle:** Update oracle-execute-sql tool interface to match source signature ([#2627](#2627)) ([81699a3](81699a3)) * Return AllParams for GetParameter() for tools with templateParameter([#2734](#2734)) ([bfd7ba6](bfd7ba6)) * **server/mcp:** Scope defer span.End inside loop iteration ([#2558](#2558)) ([c88a62d](c88a62d)), closes [#2549](#2549) * **skill:** Fix env variable propagation ([#2645](#2645)) ([5271368](5271368)) * **sources/looker:** Looker and looker-dev prebuilt tools should share one source definition. ([#2620](#2620)) ([df7f2fd](df7f2fd)) * **telemetry:** Histogram buckets from OTel standard to MCP standards ([#2729](#2729)) ([87cd4a0](87cd4a0)) * **ui:** Remove module from script ([#2703](#2703)) ([6943ab6](6943ab6)) * Update toolset attributes naming ([#2554](#2554)) ([3d6ae4e](3d6ae4e)) --- 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 <45984206+Yuan325@users.noreply.github.com>

🤖 I have created a release *beep* *boop* --- ## [0.29.0](v0.28.0...v0.29.0) (2026-03-13) ### ⚠ BREAKING CHANGES * **source/alloydb:** restructure prebuilt toolsets ([#2639](#2639)) * **source/spanner:** restructure prebuilt toolsets ([#2641](#2641)) * **source/dataplex:** restructure prebuilt toolsets ([#2640](#2640)) * **source/oss-db:** restructure prebuilt toolsets ([#2638](#2638)) * **source/cloudsql:** restructure prebuilt toolsets ([#2635](#2635)) * **source/bigquery:** restructure prebuilt toolsets ([#2637](#2637)) * **source/firestore:** restructure prebuilt toolsets ([#2636](#2636)) * telemetry metrics updates as per semantic convention ([#2566](#2566)) ### Features * Add user agent to embeddings generation ([#2572](#2572)) ([287251a](287251a)) * **skill:** Attach user agent metadata for generated skill ([#2697](#2697)) ([9598a6a](9598a6a)) * **skills:** Add additional-notes flag to generate skills command ([#2696](#2696)) ([73bf962](73bf962)) * **skill:** Update skill generation logic ([#2646](#2646)) ([c233eee](c233eee)) * **source/alloydb:** Restructure prebuilt toolsets ([#2639](#2639)) ([5f3f063](5f3f063)) * **source/bigquery:** Restructure prebuilt toolsets ([#2637](#2637)) ([dc984ba](dc984ba)) * **sources/bigquery:** Support custom oauth header name ([#2564](#2564)) ([d3baf77](d3baf77)) * **source/cloudsql:** Restructure prebuilt toolsets ([#2635](#2635)) ([99613dc](99613dc)) * **source/dataplex:** Restructure prebuilt toolsets ([#2640](#2640)) ([acb9a80](acb9a80)) * **source/firestore:** Restructure prebuilt toolsets ([#2636](#2636)) ([22ab7b9](22ab7b9)) * **source/oss-db:** Restructure prebuilt toolsets ([#2638](#2638)) ([5196c6a](5196c6a)) * **source/spanner:** Restructure prebuilt toolsets ([#2641](#2641)) ([ea2b698](ea2b698)) * Telemetry metrics updates as per semantic convention ([#2566](#2566)) ([131d764](131d764)) * **tools/mongodb:** Add tool annotations to MongoDB tools for improved LLM understanding ([#2219](#2219)) ([b7a5f80](b7a5f80)) * **tools/serverless-spark:** Add get_session_template tool ([#2308](#2308)) ([a136e16](a136e16)) * **tools/serverless-spark:** Add list/get sessions tools ([#2576](#2576)) ([a554298](a554298)) ### Bug Fixes * Improve list locks integration test for postgres ([#2279](#2279)) ([d9ebe5d](d9ebe5d)) * **mcp:** Guard nil SSE session lookup and return 400 for missing session ([#2681](#2681)) ([f66189f](f66189f)) * **oracle:** Update oracle-execute-sql tool interface to match source signature ([#2627](#2627)) ([81699a3](81699a3)) * Return AllParams for GetParameter() for tools with templateParameter([#2734](#2734)) ([bfd7ba6](bfd7ba6)) * **server/mcp:** Scope defer span.End inside loop iteration ([#2558](#2558)) ([c88a62d](c88a62d)), closes [#2549](#2549) * **skill:** Fix env variable propagation ([#2645](#2645)) ([5271368](5271368)) * **sources/looker:** Looker and looker-dev prebuilt tools should share one source definition. ([#2620](#2620)) ([df7f2fd](df7f2fd)) * **telemetry:** Histogram buckets from OTel standard to MCP standards ([#2729](#2729)) ([87cd4a0](87cd4a0)) * **ui:** Remove module from script ([#2703](#2703)) ([6943ab6](6943ab6)) * Update toolset attributes naming ([#2554](#2554)) ([3d6ae4e](3d6ae4e)) --- 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 <45984206+Yuan325@users.noreply.github.com> 39832a0

🤖 I have created a release *beep* *boop* --- ## [0.29.0](googleapis/mcp-toolbox@v0.28.0...v0.29.0) (2026-03-13) ### ⚠ BREAKING CHANGES * **source/alloydb:** restructure prebuilt toolsets ([googleapis#2639](googleapis#2639)) * **source/spanner:** restructure prebuilt toolsets ([googleapis#2641](googleapis#2641)) * **source/dataplex:** restructure prebuilt toolsets ([googleapis#2640](googleapis#2640)) * **source/oss-db:** restructure prebuilt toolsets ([googleapis#2638](googleapis#2638)) * **source/cloudsql:** restructure prebuilt toolsets ([googleapis#2635](googleapis#2635)) * **source/bigquery:** restructure prebuilt toolsets ([googleapis#2637](googleapis#2637)) * **source/firestore:** restructure prebuilt toolsets ([googleapis#2636](googleapis#2636)) * telemetry metrics updates as per semantic convention ([googleapis#2566](googleapis#2566)) ### Features * Add user agent to embeddings generation ([googleapis#2572](googleapis#2572)) ([287251a](googleapis@287251a)) * **skill:** Attach user agent metadata for generated skill ([googleapis#2697](googleapis#2697)) ([9598a6a](googleapis@9598a6a)) * **skills:** Add additional-notes flag to generate skills command ([googleapis#2696](googleapis#2696)) ([73bf962](googleapis@73bf962)) * **skill:** Update skill generation logic ([googleapis#2646](googleapis#2646)) ([c233eee](googleapis@c233eee)) * **source/alloydb:** Restructure prebuilt toolsets ([googleapis#2639](googleapis#2639)) ([5f3f063](googleapis@5f3f063)) * **source/bigquery:** Restructure prebuilt toolsets ([googleapis#2637](googleapis#2637)) ([dc984ba](googleapis@dc984ba)) * **sources/bigquery:** Support custom oauth header name ([googleapis#2564](googleapis#2564)) ([d3baf77](googleapis@d3baf77)) * **source/cloudsql:** Restructure prebuilt toolsets ([googleapis#2635](googleapis#2635)) ([99613dc](googleapis@99613dc)) * **source/dataplex:** Restructure prebuilt toolsets ([googleapis#2640](googleapis#2640)) ([acb9a80](googleapis@acb9a80)) * **source/firestore:** Restructure prebuilt toolsets ([googleapis#2636](googleapis#2636)) ([22ab7b9](googleapis@22ab7b9)) * **source/oss-db:** Restructure prebuilt toolsets ([googleapis#2638](googleapis#2638)) ([5196c6a](googleapis@5196c6a)) * **source/spanner:** Restructure prebuilt toolsets ([googleapis#2641](googleapis#2641)) ([ea2b698](googleapis@ea2b698)) * Telemetry metrics updates as per semantic convention ([googleapis#2566](googleapis#2566)) ([131d764](googleapis@131d764)) * **tools/mongodb:** Add tool annotations to MongoDB tools for improved LLM understanding ([googleapis#2219](googleapis#2219)) ([b7a5f80](googleapis@b7a5f80)) * **tools/serverless-spark:** Add get_session_template tool ([googleapis#2308](googleapis#2308)) ([a136e16](googleapis@a136e16)) * **tools/serverless-spark:** Add list/get sessions tools ([googleapis#2576](googleapis#2576)) ([a554298](googleapis@a554298)) ### Bug Fixes * Improve list locks integration test for postgres ([googleapis#2279](googleapis#2279)) ([d9ebe5d](googleapis@d9ebe5d)) * **mcp:** Guard nil SSE session lookup and return 400 for missing session ([googleapis#2681](googleapis#2681)) ([f66189f](googleapis@f66189f)) * **oracle:** Update oracle-execute-sql tool interface to match source signature ([googleapis#2627](googleapis#2627)) ([81699a3](googleapis@81699a3)) * Return AllParams for GetParameter() for tools with templateParameter([googleapis#2734](googleapis#2734)) ([bfd7ba6](googleapis@bfd7ba6)) * **server/mcp:** Scope defer span.End inside loop iteration ([googleapis#2558](googleapis#2558)) ([c88a62d](googleapis@c88a62d)), closes [googleapis#2549](googleapis#2549) * **skill:** Fix env variable propagation ([googleapis#2645](googleapis#2645)) ([5271368](googleapis@5271368)) * **sources/looker:** Looker and looker-dev prebuilt tools should share one source definition. ([googleapis#2620](googleapis#2620)) ([df7f2fd](googleapis@df7f2fd)) * **telemetry:** Histogram buckets from OTel standard to MCP standards ([googleapis#2729](googleapis#2729)) ([87cd4a0](googleapis@87cd4a0)) * **ui:** Remove module from script ([googleapis#2703](googleapis#2703)) ([6943ab6](googleapis@6943ab6)) * Update toolset attributes naming ([googleapis#2554](googleapis#2554)) ([3d6ae4e](googleapis@3d6ae4e)) --- 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 <45984206+Yuan325@users.noreply.github.com> 39832a0

🤖 I have created a release *beep* *boop* --- ## [0.29.0](googleapis/mcp-toolbox@v0.28.0...v0.29.0) (2026-03-13) ### ⚠ BREAKING CHANGES * **source/alloydb:** restructure prebuilt toolsets ([#2639](googleapis/mcp-toolbox#2639)) * **source/spanner:** restructure prebuilt toolsets ([#2641](googleapis/mcp-toolbox#2641)) * **source/dataplex:** restructure prebuilt toolsets ([#2640](googleapis/mcp-toolbox#2640)) * **source/oss-db:** restructure prebuilt toolsets ([#2638](googleapis/mcp-toolbox#2638)) * **source/cloudsql:** restructure prebuilt toolsets ([#2635](googleapis/mcp-toolbox#2635)) * **source/bigquery:** restructure prebuilt toolsets ([#2637](googleapis/mcp-toolbox#2637)) * **source/firestore:** restructure prebuilt toolsets ([#2636](googleapis/mcp-toolbox#2636)) * telemetry metrics updates as per semantic convention ([#2566](googleapis/mcp-toolbox#2566)) ### Features * Add user agent to embeddings generation ([#2572](googleapis/mcp-toolbox#2572)) ([287251a](googleapis/mcp-toolbox@287251a)) * **skill:** Attach user agent metadata for generated skill ([#2697](googleapis/mcp-toolbox#2697)) ([9598a6a](googleapis/mcp-toolbox@9598a6a)) * **skills:** Add additional-notes flag to generate skills command ([#2696](googleapis/mcp-toolbox#2696)) ([73bf962](googleapis/mcp-toolbox@73bf962)) * **skill:** Update skill generation logic ([#2646](googleapis/mcp-toolbox#2646)) ([c233eee](googleapis/mcp-toolbox@c233eee)) * **source/alloydb:** Restructure prebuilt toolsets ([#2639](googleapis/mcp-toolbox#2639)) ([5f3f063](googleapis/mcp-toolbox@5f3f063)) * **source/bigquery:** Restructure prebuilt toolsets ([#2637](googleapis/mcp-toolbox#2637)) ([dc984ba](googleapis/mcp-toolbox@dc984ba)) * **sources/bigquery:** Support custom oauth header name ([#2564](googleapis/mcp-toolbox#2564)) ([d3baf77](googleapis/mcp-toolbox@d3baf77)) * **source/cloudsql:** Restructure prebuilt toolsets ([#2635](googleapis/mcp-toolbox#2635)) ([99613dc](googleapis/mcp-toolbox@99613dc)) * **source/dataplex:** Restructure prebuilt toolsets ([#2640](googleapis/mcp-toolbox#2640)) ([acb9a80](googleapis/mcp-toolbox@acb9a80)) * **source/firestore:** Restructure prebuilt toolsets ([#2636](googleapis/mcp-toolbox#2636)) ([22ab7b9](googleapis/mcp-toolbox@22ab7b9)) * **source/oss-db:** Restructure prebuilt toolsets ([#2638](googleapis/mcp-toolbox#2638)) ([5196c6a](googleapis/mcp-toolbox@5196c6a)) * **source/spanner:** Restructure prebuilt toolsets ([#2641](googleapis/mcp-toolbox#2641)) ([ea2b698](googleapis/mcp-toolbox@ea2b698)) * Telemetry metrics updates as per semantic convention ([#2566](googleapis/mcp-toolbox#2566)) ([131d764](googleapis/mcp-toolbox@131d764)) * **tools/mongodb:** Add tool annotations to MongoDB tools for improved LLM understanding ([#2219](googleapis/mcp-toolbox#2219)) ([b7a5f80](googleapis/mcp-toolbox@b7a5f80)) * **tools/serverless-spark:** Add get_session_template tool ([#2308](googleapis/mcp-toolbox#2308)) ([a136e16](googleapis/mcp-toolbox@a136e16)) * **tools/serverless-spark:** Add list/get sessions tools ([#2576](googleapis/mcp-toolbox#2576)) ([a554298](googleapis/mcp-toolbox@a554298)) ### Bug Fixes * Improve list locks integration test for postgres ([#2279](googleapis/mcp-toolbox#2279)) ([d9ebe5d](googleapis/mcp-toolbox@d9ebe5d)) * **mcp:** Guard nil SSE session lookup and return 400 for missing session ([#2681](googleapis/mcp-toolbox#2681)) ([f66189f](googleapis/mcp-toolbox@f66189f)) * **oracle:** Update oracle-execute-sql tool interface to match source signature ([#2627](googleapis/mcp-toolbox#2627)) ([81699a3](googleapis/mcp-toolbox@81699a3)) * Return AllParams for GetParameter() for tools with templateParameter([#2734](googleapis/mcp-toolbox#2734)) ([bfd7ba6](googleapis/mcp-toolbox@bfd7ba6)) * **server/mcp:** Scope defer span.End inside loop iteration ([#2558](googleapis/mcp-toolbox#2558)) ([c88a62d](googleapis/mcp-toolbox@c88a62d)), closes [#2549](googleapis/mcp-toolbox#2549) * **skill:** Fix env variable propagation ([#2645](googleapis/mcp-toolbox#2645)) ([5271368](googleapis/mcp-toolbox@5271368)) * **sources/looker:** Looker and looker-dev prebuilt tools should share one source definition. ([#2620](googleapis/mcp-toolbox#2620)) ([df7f2fd](googleapis/mcp-toolbox@df7f2fd)) * **telemetry:** Histogram buckets from OTel standard to MCP standards ([#2729](googleapis/mcp-toolbox#2729)) ([87cd4a0](googleapis/mcp-toolbox@87cd4a0)) * **ui:** Remove module from script ([#2703](googleapis/mcp-toolbox#2703)) ([6943ab6](googleapis/mcp-toolbox@6943ab6)) * Update toolset attributes naming ([#2554](googleapis/mcp-toolbox#2554)) ([3d6ae4e](googleapis/mcp-toolbox@3d6ae4e)) --- 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 <45984206+Yuan325@users.noreply.github.com>

## Description Adds commands for Serverless Spark sessions analogous to existing list/get commands for batches. Unlike batches, we don't plan to add create session commands, as these are generally only created via the Jupyter protocol. Agents will need to have other ways to create sessions, for example by interacting directly with an IDE like Jupyter Lab or VS Code, but those won't be part of MCP Toolbox. ## 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](https://github.com/googleapis/genai-toolbox/blob/main/CONTRIBUTING.md) - [ ] Make sure to open an issue as a [bug/issue](https://github.com/googleapis/genai-toolbox/issues/new/choose) 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 🛠️ Part of googleapis#2405 Co-authored-by: Wenxin Du <117315983+duwenxin99@users.noreply.github.com>

🤖 I have created a release *beep* *boop* --- ## [0.29.0](googleapis/mcp-toolbox@v0.28.0...v0.29.0) (2026-03-13) ### ⚠ BREAKING CHANGES * **source/alloydb:** restructure prebuilt toolsets ([googleapis#2639](googleapis#2639)) * **source/spanner:** restructure prebuilt toolsets ([googleapis#2641](googleapis#2641)) * **source/dataplex:** restructure prebuilt toolsets ([googleapis#2640](googleapis#2640)) * **source/oss-db:** restructure prebuilt toolsets ([googleapis#2638](googleapis#2638)) * **source/cloudsql:** restructure prebuilt toolsets ([googleapis#2635](googleapis#2635)) * **source/bigquery:** restructure prebuilt toolsets ([googleapis#2637](googleapis#2637)) * **source/firestore:** restructure prebuilt toolsets ([googleapis#2636](googleapis#2636)) * telemetry metrics updates as per semantic convention ([googleapis#2566](googleapis#2566)) ### Features * Add user agent to embeddings generation ([googleapis#2572](googleapis#2572)) ([287251a](googleapis@287251a)) * **skill:** Attach user agent metadata for generated skill ([googleapis#2697](googleapis#2697)) ([9598a6a](googleapis@9598a6a)) * **skills:** Add additional-notes flag to generate skills command ([googleapis#2696](googleapis#2696)) ([73bf962](googleapis@73bf962)) * **skill:** Update skill generation logic ([googleapis#2646](googleapis#2646)) ([c233eee](googleapis@c233eee)) * **source/alloydb:** Restructure prebuilt toolsets ([googleapis#2639](googleapis#2639)) ([5f3f063](googleapis@5f3f063)) * **source/bigquery:** Restructure prebuilt toolsets ([googleapis#2637](googleapis#2637)) ([dc984ba](googleapis@dc984ba)) * **sources/bigquery:** Support custom oauth header name ([googleapis#2564](googleapis#2564)) ([d3baf77](googleapis@d3baf77)) * **source/cloudsql:** Restructure prebuilt toolsets ([googleapis#2635](googleapis#2635)) ([99613dc](googleapis@99613dc)) * **source/dataplex:** Restructure prebuilt toolsets ([googleapis#2640](googleapis#2640)) ([acb9a80](googleapis@acb9a80)) * **source/firestore:** Restructure prebuilt toolsets ([googleapis#2636](googleapis#2636)) ([22ab7b9](googleapis@22ab7b9)) * **source/oss-db:** Restructure prebuilt toolsets ([googleapis#2638](googleapis#2638)) ([5196c6a](googleapis@5196c6a)) * **source/spanner:** Restructure prebuilt toolsets ([googleapis#2641](googleapis#2641)) ([ea2b698](googleapis@ea2b698)) * Telemetry metrics updates as per semantic convention ([googleapis#2566](googleapis#2566)) ([131d764](googleapis@131d764)) * **tools/mongodb:** Add tool annotations to MongoDB tools for improved LLM understanding ([googleapis#2219](googleapis#2219)) ([b7a5f80](googleapis@b7a5f80)) * **tools/serverless-spark:** Add get_session_template tool ([googleapis#2308](googleapis#2308)) ([a136e16](googleapis@a136e16)) * **tools/serverless-spark:** Add list/get sessions tools ([googleapis#2576](googleapis#2576)) ([a554298](googleapis@a554298)) ### Bug Fixes * Improve list locks integration test for postgres ([googleapis#2279](googleapis#2279)) ([d9ebe5d](googleapis@d9ebe5d)) * **mcp:** Guard nil SSE session lookup and return 400 for missing session ([googleapis#2681](googleapis#2681)) ([f66189f](googleapis@f66189f)) * **oracle:** Update oracle-execute-sql tool interface to match source signature ([googleapis#2627](googleapis#2627)) ([81699a3](googleapis@81699a3)) * Return AllParams for GetParameter() for tools with templateParameter([googleapis#2734](googleapis#2734)) ([bfd7ba6](googleapis@bfd7ba6)) * **server/mcp:** Scope defer span.End inside loop iteration ([googleapis#2558](googleapis#2558)) ([c88a62d](googleapis@c88a62d)), closes [googleapis#2549](googleapis#2549) * **skill:** Fix env variable propagation ([googleapis#2645](googleapis#2645)) ([5271368](googleapis@5271368)) * **sources/looker:** Looker and looker-dev prebuilt tools should share one source definition. ([googleapis#2620](googleapis#2620)) ([df7f2fd](googleapis@df7f2fd)) * **telemetry:** Histogram buckets from OTel standard to MCP standards ([googleapis#2729](googleapis#2729)) ([87cd4a0](googleapis@87cd4a0)) * **ui:** Remove module from script ([googleapis#2703](googleapis#2703)) ([6943ab6](googleapis@6943ab6)) * Update toolset attributes naming ([googleapis#2554](googleapis#2554)) ([3d6ae4e](googleapis@3d6ae4e)) --- 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 <45984206+Yuan325@users.noreply.github.com>

dborowitz requested a review from a team as a code owner February 27, 2026 17:48

blunderbuss-gcf Bot assigned duwenxin99 Feb 27, 2026

gemini-code-assist Bot reviewed Feb 27, 2026

View reviewed changes

Comment thread docs/en/resources/tools/serverless-spark/serverless-spark-get-session.md Outdated

Comment thread docs/en/resources/tools/serverless-spark/serverless-spark-list-sessions.md Outdated

Comment thread tests/serverlessspark/serverless_spark_integration_test.go Outdated

dborowitz force-pushed the sessions branch 2 times, most recently from 7ab6c35 to 73c81e6 Compare February 27, 2026 18:26

dborowitz added the docs: deploy-preview Label to trigger Github Action docs preview. label Feb 27, 2026

duwenxin99 approved these changes Feb 27, 2026

View reviewed changes

Comment thread docs/en/resources/tools/serverless-spark/serverless-spark-list-sessions.md

dborowitz force-pushed the sessions branch 2 times, most recently from 5dfb43b to 449ee6f Compare February 27, 2026 21:32

dborowitz added the tests: run Label to trigger Github Action tests. label Feb 27, 2026

dborowitz enabled auto-merge (rebase) February 27, 2026 21:32

github-actions Bot removed the tests: run Label to trigger Github Action tests. label Feb 27, 2026

dborowitz force-pushed the sessions branch 2 times, most recently from b3026da to a39ec88 Compare March 2, 2026 16:49

dborowitz added the tests: run Label to trigger Github Action tests. label Mar 2, 2026

github-actions Bot removed the tests: run Label to trigger Github Action tests. label Mar 2, 2026

feat(serverless-spark): add list/get sessions commands

d2c0a58

auto-merge was automatically disabled March 3, 2026 16:21
Head branch was pushed to by a user without write access

dborowitz force-pushed the sessions branch from a39ec88 to d2c0a58 Compare March 3, 2026 16:21

duwenxin99 and others added 2 commits March 3, 2026 14:26

Merge branch 'main' into sessions

bb7ce74

Merge branch 'main' into sessions

01760bd

duwenxin99 enabled auto-merge (squash) March 4, 2026 02:59

duwenxin99 merged commit a554298 into googleapis:main Mar 4, 2026
19 checks passed

release-please Bot mentioned this pull request Mar 3, 2026

chore(main): release 0.29.0 #2608

Merged

BrewTestBot mentioned this pull request Mar 13, 2026

mcp-toolbox 0.29.0 Homebrew/homebrew-core#272217

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat(serverless-spark): add list/get sessions commands#2576

feat(serverless-spark): add list/get sessions commands#2576
duwenxin99 merged 3 commits into
googleapis:mainfrom
dborowitz:sessions

dborowitz commented Feb 27, 2026

Uh oh!

gemini-code-assist Bot commented Feb 27, 2026

Uh oh!

gemini-code-assist Bot left a comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

github-actions Bot commented Feb 27, 2026

Uh oh!

dborowitz commented Feb 27, 2026

Uh oh!

Uh oh!

duwenxin99 commented Mar 3, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

dborowitz commented Feb 27, 2026

Description

PR Checklist

Uh oh!

gemini-code-assist Bot commented Feb 27, 2026

Summary of Changes

Highlights

Footnotes

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!

github-actions Bot commented Feb 27, 2026

Uh oh!

dborowitz commented Feb 27, 2026

Uh oh!

Uh oh!

duwenxin99 commented Mar 3, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants