feat: support alternate accessToken header name#1968
Conversation
Summary of ChangesHello @drstrangelooker, 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 enhances the system's flexibility by allowing the Highlights
Using Gemini Code AssistThe 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
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 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. Footnotes
|
There was a problem hiding this comment.
Code Review
This pull request introduces a valuable feature by allowing the accessToken header name to be configurable, defaulting to Authorization. The changes are well-implemented across the board, with the new AccessTokenHeader() method added to the Tool interface and correctly implemented in most tools. However, I've identified one critical issue where a field in a Looker tool is not initialized, which will lead to authentication failures. Please see the specific comment for details.
|
@averikitsch @kurtisvg This is what I have so far. |
f557229 to
01c6ec8
Compare
1 similar comment
5abb71a to
38165f2
Compare
38165f2 to
761b51f
Compare
1 similar comment
a029338 to
e31e540
Compare
e31e540 to
79e73a1
Compare
79e73a1 to
13afb3c
Compare
13afb3c to
83e2bbe
Compare
c582c32 to
3367d56
Compare
3367d56 to
5b056f1
Compare
|
@duwenxin99 This has been reviewed by Kurtis and Averi. Can you take a look too? Thanks |
|
🧨 Preview deployments removed. |
## Description This commit allows a tool to pull an alternate authorization token from the header of the http request. This is initially being built for the Looker integration. Looker uses its own OAuth token. When deploying MCP Toolbox to Cloud Run, the default token in the "Authorization" header is for authentication with Cloud Run. An alternate token can be put into another header by a client such as ADK or any other client that can programatically set http headers. This token will be used to authenticate with Looker. If needed, other sources can use this by setting the header name in the source config, passing it into the tool config, and returning the header name in the Tool GetAuthTokenHeaderName() function. ## 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/genai-toolbox/blob/main/CONTRIBUTING.md) - [x] 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 - [x] Ensure the tests and linter pass - [x] Code coverage does not decrease (if any source code was changed) - [x] Appropriate docs were updated (if necessary) - [x] Make sure to add `!` if this involve a breaking change 🛠️ Fixes #1540 18017d6
## Description This commit allows a tool to pull an alternate authorization token from the header of the http request. This is initially being built for the Looker integration. Looker uses its own OAuth token. When deploying MCP Toolbox to Cloud Run, the default token in the "Authorization" header is for authentication with Cloud Run. An alternate token can be put into another header by a client such as ADK or any other client that can programatically set http headers. This token will be used to authenticate with Looker. If needed, other sources can use this by setting the header name in the source config, passing it into the tool config, and returning the header name in the Tool GetAuthTokenHeaderName() function. ## 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/genai-toolbox/blob/main/CONTRIBUTING.md) - [x] 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 - [x] Ensure the tests and linter pass - [x] Code coverage does not decrease (if any source code was changed) - [x] Appropriate docs were updated (if necessary) - [x] Make sure to add `!` if this involve a breaking change 🛠️ Fixes #1540 18017d6
) ## Description This commit allows a tool to pull an alternate authorization token from the header of the http request. This is initially being built for the Looker integration. Looker uses its own OAuth token. When deploying MCP Toolbox to Cloud Run, the default token in the "Authorization" header is for authentication with Cloud Run. An alternate token can be put into another header by a client such as ADK or any other client that can programatically set http headers. This token will be used to authenticate with Looker. If needed, other sources can use this by setting the header name in the source config, passing it into the tool config, and returning the header name in the Tool GetAuthTokenHeaderName() function. ## 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/genai-toolbox/blob/main/CONTRIBUTING.md) - [x] 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 - [x] Ensure the tests and linter pass - [x] Code coverage does not decrease (if any source code was changed) - [x] Appropriate docs were updated (if necessary) - [x] Make sure to add `!` if this involve a breaking change 🛠️ Fixes googleapis#1540 18017d6
) ## Description This commit allows a tool to pull an alternate authorization token from the header of the http request. This is initially being built for the Looker integration. Looker uses its own OAuth token. When deploying MCP Toolbox to Cloud Run, the default token in the "Authorization" header is for authentication with Cloud Run. An alternate token can be put into another header by a client such as ADK or any other client that can programatically set http headers. This token will be used to authenticate with Looker. If needed, other sources can use this by setting the header name in the source config, passing it into the tool config, and returning the header name in the Tool GetAuthTokenHeaderName() function. ## 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/genai-toolbox/blob/main/CONTRIBUTING.md) - [x] 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 - [x] Ensure the tests and linter pass - [x] Code coverage does not decrease (if any source code was changed) - [x] Appropriate docs were updated (if necessary) - [x] Make sure to add `!` if this involve a breaking change 🛠️ Fixes googleapis#1540 18017d6
) ## Description This commit allows a tool to pull an alternate authorization token from the header of the http request. This is initially being built for the Looker integration. Looker uses its own OAuth token. When deploying MCP Toolbox to Cloud Run, the default token in the "Authorization" header is for authentication with Cloud Run. An alternate token can be put into another header by a client such as ADK or any other client that can programatically set http headers. This token will be used to authenticate with Looker. If needed, other sources can use this by setting the header name in the source config, passing it into the tool config, and returning the header name in the Tool GetAuthTokenHeaderName() function. ## 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/genai-toolbox/blob/main/CONTRIBUTING.md) - [x] 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 - [x] Ensure the tests and linter pass - [x] Code coverage does not decrease (if any source code was changed) - [x] Appropriate docs were updated (if necessary) - [x] Make sure to add `!` if this involve a breaking change 🛠️ Fixes googleapis#1540 18017d6
) ## Description This commit allows a tool to pull an alternate authorization token from the header of the http request. This is initially being built for the Looker integration. Looker uses its own OAuth token. When deploying MCP Toolbox to Cloud Run, the default token in the "Authorization" header is for authentication with Cloud Run. An alternate token can be put into another header by a client such as ADK or any other client that can programatically set http headers. This token will be used to authenticate with Looker. If needed, other sources can use this by setting the header name in the source config, passing it into the tool config, and returning the header name in the Tool GetAuthTokenHeaderName() function. ## 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/genai-toolbox/blob/main/CONTRIBUTING.md) - [x] 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 - [x] Ensure the tests and linter pass - [x] Code coverage does not decrease (if any source code was changed) - [x] Appropriate docs were updated (if necessary) - [x] Make sure to add `!` if this involve a breaking change 🛠️ Fixes googleapis#1540 18017d6
🤖 I have created a release *beep* *boop* --- ## [0.22.0](v0.21.0...v0.22.0) (2025-12-04) ### Features * Add allowed-origins flag ([#1984](#1984)) ([862868f](862868f)) * **tools/postgres:** Add list-query-stats and get-column-cardinality functions ([#1976](#1976)) ([9f76026](9f76026)) * **tools/spanner:** Add spanner list graphs to prebuiltconfigs ([#2056](#2056)) ([0e7fbf4](0e7fbf4)) * **prebuilt/cloud-sql:** Add clone instance tool for cloud sql ([#1845](#1845)) ([5e43630](5e43630)) * **serverless-spark:** Add create_pyspark_batch tool ([1bf0b51](1bf0b51)) * **serverless-spark:** Add create_spark_batch tool ([17a9792](17a9792)) * Support alternate accessToken header name ([#1968](#1968)) ([18017d6](18017d6)) * Support for annotations ([#2007](#2007)) ([ac21335](ac21335)) * **tool/mssql:** Set default host and port for MSSQL source ([#1943](#1943)) ([7a9cc63](7a9cc63)) * **tools/cloudsqlpg:** Add CloudSQL PostgreSQL pre-check tool ([#1722](#1722)) ([8752e05](8752e05)) * **tools/postgres-list-publication-tables:** Add new postgres-list-publication-tables tool ([#1919](#1919)) ([f4b1f0a](f4b1f0a)) * **tools/postgres-list-tablespaces:** Add new postgres-list-tablespaces tool ([#1934](#1934)) ([5ad7c61](5ad7c61)) * **tools/spanner-list-graph:** Tool impl + docs + tests ([#1923](#1923)) ([a0f44d3](a0f44d3)) ### Bug Fixes * Add import for firebirdsql ([#2045](#2045)) ([fb7aae9](fb7aae9)) * Correct FAQ to mention HTTP tools ([#2036](#2036)) ([7b44237](7b44237)) * Format BigQuery numeric output as decimal strings ([#2084](#2084)) ([155bff8](155bff8)) * Set default annotations for tools in code if annotation not provided in yaml ([#2049](#2049)) ([565460c](565460c)) * **tools/alloydb-postgres-list-tables:** Exclude google_ml schema from list_tables ([#2046](#2046)) ([a03984c](a03984c)) * **tools/alloydbcreateuser:** Remove duplication of project praram ([#2028](#2028)) ([730ac6d](730ac6d)) * **tools/mongodb:** Remove `required` tag from the `canonical` field ([#2099](#2099)) ([744214e](744214e)) --- 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: Wenxin Du <117315983+duwenxin99@users.noreply.github.com>
🤖 I have created a release *beep* *boop* --- ## [0.22.0](v0.21.0...v0.22.0) (2025-12-04) ### Features * Add allowed-origins flag ([#1984](#1984)) ([862868f](862868f)) * **tools/postgres:** Add list-query-stats and get-column-cardinality functions ([#1976](#1976)) ([9f76026](9f76026)) * **tools/spanner:** Add spanner list graphs to prebuiltconfigs ([#2056](#2056)) ([0e7fbf4](0e7fbf4)) * **prebuilt/cloud-sql:** Add clone instance tool for cloud sql ([#1845](#1845)) ([5e43630](5e43630)) * **serverless-spark:** Add create_pyspark_batch tool ([1bf0b51](1bf0b51)) * **serverless-spark:** Add create_spark_batch tool ([17a9792](17a9792)) * Support alternate accessToken header name ([#1968](#1968)) ([18017d6](18017d6)) * Support for annotations ([#2007](#2007)) ([ac21335](ac21335)) * **tool/mssql:** Set default host and port for MSSQL source ([#1943](#1943)) ([7a9cc63](7a9cc63)) * **tools/cloudsqlpg:** Add CloudSQL PostgreSQL pre-check tool ([#1722](#1722)) ([8752e05](8752e05)) * **tools/postgres-list-publication-tables:** Add new postgres-list-publication-tables tool ([#1919](#1919)) ([f4b1f0a](f4b1f0a)) * **tools/postgres-list-tablespaces:** Add new postgres-list-tablespaces tool ([#1934](#1934)) ([5ad7c61](5ad7c61)) * **tools/spanner-list-graph:** Tool impl + docs + tests ([#1923](#1923)) ([a0f44d3](a0f44d3)) ### Bug Fixes * Add import for firebirdsql ([#2045](#2045)) ([fb7aae9](fb7aae9)) * Correct FAQ to mention HTTP tools ([#2036](#2036)) ([7b44237](7b44237)) * Format BigQuery numeric output as decimal strings ([#2084](#2084)) ([155bff8](155bff8)) * Set default annotations for tools in code if annotation not provided in yaml ([#2049](#2049)) ([565460c](565460c)) * **tools/alloydb-postgres-list-tables:** Exclude google_ml schema from list_tables ([#2046](#2046)) ([a03984c](a03984c)) * **tools/alloydbcreateuser:** Remove duplication of project praram ([#2028](#2028)) ([730ac6d](730ac6d)) * **tools/mongodb:** Remove `required` tag from the `canonical` field ([#2099](#2099)) ([744214e](744214e)) --- 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: Wenxin Du <117315983+duwenxin99@users.noreply.github.com> cb4529c
🤖 I have created a release *beep* *boop* --- ## [0.22.0](googleapis/mcp-toolbox@v0.21.0...v0.22.0) (2025-12-04) ### Features * Add allowed-origins flag ([googleapis#1984](googleapis#1984)) ([862868f](googleapis@862868f)) * **tools/postgres:** Add list-query-stats and get-column-cardinality functions ([googleapis#1976](googleapis#1976)) ([9f76026](googleapis@9f76026)) * **tools/spanner:** Add spanner list graphs to prebuiltconfigs ([googleapis#2056](googleapis#2056)) ([0e7fbf4](googleapis@0e7fbf4)) * **prebuilt/cloud-sql:** Add clone instance tool for cloud sql ([googleapis#1845](googleapis#1845)) ([5e43630](googleapis@5e43630)) * **serverless-spark:** Add create_pyspark_batch tool ([1bf0b51](googleapis@1bf0b51)) * **serverless-spark:** Add create_spark_batch tool ([17a9792](googleapis@17a9792)) * Support alternate accessToken header name ([googleapis#1968](googleapis#1968)) ([18017d6](googleapis@18017d6)) * Support for annotations ([googleapis#2007](googleapis#2007)) ([ac21335](googleapis@ac21335)) * **tool/mssql:** Set default host and port for MSSQL source ([googleapis#1943](googleapis#1943)) ([7a9cc63](googleapis@7a9cc63)) * **tools/cloudsqlpg:** Add CloudSQL PostgreSQL pre-check tool ([googleapis#1722](googleapis#1722)) ([8752e05](googleapis@8752e05)) * **tools/postgres-list-publication-tables:** Add new postgres-list-publication-tables tool ([googleapis#1919](googleapis#1919)) ([f4b1f0a](googleapis@f4b1f0a)) * **tools/postgres-list-tablespaces:** Add new postgres-list-tablespaces tool ([googleapis#1934](googleapis#1934)) ([5ad7c61](googleapis@5ad7c61)) * **tools/spanner-list-graph:** Tool impl + docs + tests ([googleapis#1923](googleapis#1923)) ([a0f44d3](googleapis@a0f44d3)) ### Bug Fixes * Add import for firebirdsql ([googleapis#2045](googleapis#2045)) ([fb7aae9](googleapis@fb7aae9)) * Correct FAQ to mention HTTP tools ([googleapis#2036](googleapis#2036)) ([7b44237](googleapis@7b44237)) * Format BigQuery numeric output as decimal strings ([googleapis#2084](googleapis#2084)) ([155bff8](googleapis@155bff8)) * Set default annotations for tools in code if annotation not provided in yaml ([googleapis#2049](googleapis#2049)) ([565460c](googleapis@565460c)) * **tools/alloydb-postgres-list-tables:** Exclude google_ml schema from list_tables ([googleapis#2046](googleapis#2046)) ([a03984c](googleapis@a03984c)) * **tools/alloydbcreateuser:** Remove duplication of project praram ([googleapis#2028](googleapis#2028)) ([730ac6d](googleapis@730ac6d)) * **tools/mongodb:** Remove `required` tag from the `canonical` field ([googleapis#2099](googleapis#2099)) ([744214e](googleapis@744214e)) --- 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: Wenxin Du <117315983+duwenxin99@users.noreply.github.com> cb4529c
🤖 I have created a release *beep* *boop* --- ## [0.22.0](googleapis/mcp-toolbox@v0.21.0...v0.22.0) (2025-12-04) ### Features * Add allowed-origins flag ([googleapis#1984](googleapis#1984)) ([862868f](googleapis@862868f)) * **tools/postgres:** Add list-query-stats and get-column-cardinality functions ([googleapis#1976](googleapis#1976)) ([9f76026](googleapis@9f76026)) * **tools/spanner:** Add spanner list graphs to prebuiltconfigs ([googleapis#2056](googleapis#2056)) ([0e7fbf4](googleapis@0e7fbf4)) * **prebuilt/cloud-sql:** Add clone instance tool for cloud sql ([googleapis#1845](googleapis#1845)) ([5e43630](googleapis@5e43630)) * **serverless-spark:** Add create_pyspark_batch tool ([1bf0b51](googleapis@1bf0b51)) * **serverless-spark:** Add create_spark_batch tool ([17a9792](googleapis@17a9792)) * Support alternate accessToken header name ([googleapis#1968](googleapis#1968)) ([18017d6](googleapis@18017d6)) * Support for annotations ([googleapis#2007](googleapis#2007)) ([ac21335](googleapis@ac21335)) * **tool/mssql:** Set default host and port for MSSQL source ([googleapis#1943](googleapis#1943)) ([7a9cc63](googleapis@7a9cc63)) * **tools/cloudsqlpg:** Add CloudSQL PostgreSQL pre-check tool ([googleapis#1722](googleapis#1722)) ([8752e05](googleapis@8752e05)) * **tools/postgres-list-publication-tables:** Add new postgres-list-publication-tables tool ([googleapis#1919](googleapis#1919)) ([f4b1f0a](googleapis@f4b1f0a)) * **tools/postgres-list-tablespaces:** Add new postgres-list-tablespaces tool ([googleapis#1934](googleapis#1934)) ([5ad7c61](googleapis@5ad7c61)) * **tools/spanner-list-graph:** Tool impl + docs + tests ([googleapis#1923](googleapis#1923)) ([a0f44d3](googleapis@a0f44d3)) ### Bug Fixes * Add import for firebirdsql ([googleapis#2045](googleapis#2045)) ([fb7aae9](googleapis@fb7aae9)) * Correct FAQ to mention HTTP tools ([googleapis#2036](googleapis#2036)) ([7b44237](googleapis@7b44237)) * Format BigQuery numeric output as decimal strings ([googleapis#2084](googleapis#2084)) ([155bff8](googleapis@155bff8)) * Set default annotations for tools in code if annotation not provided in yaml ([googleapis#2049](googleapis#2049)) ([565460c](googleapis@565460c)) * **tools/alloydb-postgres-list-tables:** Exclude google_ml schema from list_tables ([googleapis#2046](googleapis#2046)) ([a03984c](googleapis@a03984c)) * **tools/alloydbcreateuser:** Remove duplication of project praram ([googleapis#2028](googleapis#2028)) ([730ac6d](googleapis@730ac6d)) * **tools/mongodb:** Remove `required` tag from the `canonical` field ([googleapis#2099](googleapis#2099)) ([744214e](googleapis@744214e)) --- 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: Wenxin Du <117315983+duwenxin99@users.noreply.github.com> cb4529c
🤖 I have created a release *beep* *boop* --- ## [0.22.0](googleapis/mcp-toolbox@v0.21.0...v0.22.0) (2025-12-04) ### Features * Add allowed-origins flag ([googleapis#1984](googleapis#1984)) ([862868f](googleapis@862868f)) * **tools/postgres:** Add list-query-stats and get-column-cardinality functions ([googleapis#1976](googleapis#1976)) ([9f76026](googleapis@9f76026)) * **tools/spanner:** Add spanner list graphs to prebuiltconfigs ([googleapis#2056](googleapis#2056)) ([0e7fbf4](googleapis@0e7fbf4)) * **prebuilt/cloud-sql:** Add clone instance tool for cloud sql ([googleapis#1845](googleapis#1845)) ([5e43630](googleapis@5e43630)) * **serverless-spark:** Add create_pyspark_batch tool ([1bf0b51](googleapis@1bf0b51)) * **serverless-spark:** Add create_spark_batch tool ([17a9792](googleapis@17a9792)) * Support alternate accessToken header name ([googleapis#1968](googleapis#1968)) ([18017d6](googleapis@18017d6)) * Support for annotations ([googleapis#2007](googleapis#2007)) ([ac21335](googleapis@ac21335)) * **tool/mssql:** Set default host and port for MSSQL source ([googleapis#1943](googleapis#1943)) ([7a9cc63](googleapis@7a9cc63)) * **tools/cloudsqlpg:** Add CloudSQL PostgreSQL pre-check tool ([googleapis#1722](googleapis#1722)) ([8752e05](googleapis@8752e05)) * **tools/postgres-list-publication-tables:** Add new postgres-list-publication-tables tool ([googleapis#1919](googleapis#1919)) ([f4b1f0a](googleapis@f4b1f0a)) * **tools/postgres-list-tablespaces:** Add new postgres-list-tablespaces tool ([googleapis#1934](googleapis#1934)) ([5ad7c61](googleapis@5ad7c61)) * **tools/spanner-list-graph:** Tool impl + docs + tests ([googleapis#1923](googleapis#1923)) ([a0f44d3](googleapis@a0f44d3)) ### Bug Fixes * Add import for firebirdsql ([googleapis#2045](googleapis#2045)) ([fb7aae9](googleapis@fb7aae9)) * Correct FAQ to mention HTTP tools ([googleapis#2036](googleapis#2036)) ([7b44237](googleapis@7b44237)) * Format BigQuery numeric output as decimal strings ([googleapis#2084](googleapis#2084)) ([155bff8](googleapis@155bff8)) * Set default annotations for tools in code if annotation not provided in yaml ([googleapis#2049](googleapis#2049)) ([565460c](googleapis@565460c)) * **tools/alloydb-postgres-list-tables:** Exclude google_ml schema from list_tables ([googleapis#2046](googleapis#2046)) ([a03984c](googleapis@a03984c)) * **tools/alloydbcreateuser:** Remove duplication of project praram ([googleapis#2028](googleapis#2028)) ([730ac6d](googleapis@730ac6d)) * **tools/mongodb:** Remove `required` tag from the `canonical` field ([googleapis#2099](googleapis#2099)) ([744214e](googleapis@744214e)) --- 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: Wenxin Du <117315983+duwenxin99@users.noreply.github.com> cb4529c
🤖 I have created a release *beep* *boop* --- ## [0.22.0](googleapis/mcp-toolbox@v0.21.0...v0.22.0) (2025-12-04) ### Features * Add allowed-origins flag ([googleapis#1984](googleapis#1984)) ([862868f](googleapis@862868f)) * **tools/postgres:** Add list-query-stats and get-column-cardinality functions ([googleapis#1976](googleapis#1976)) ([9f76026](googleapis@9f76026)) * **tools/spanner:** Add spanner list graphs to prebuiltconfigs ([googleapis#2056](googleapis#2056)) ([0e7fbf4](googleapis@0e7fbf4)) * **prebuilt/cloud-sql:** Add clone instance tool for cloud sql ([googleapis#1845](googleapis#1845)) ([5e43630](googleapis@5e43630)) * **serverless-spark:** Add create_pyspark_batch tool ([1bf0b51](googleapis@1bf0b51)) * **serverless-spark:** Add create_spark_batch tool ([17a9792](googleapis@17a9792)) * Support alternate accessToken header name ([googleapis#1968](googleapis#1968)) ([18017d6](googleapis@18017d6)) * Support for annotations ([googleapis#2007](googleapis#2007)) ([ac21335](googleapis@ac21335)) * **tool/mssql:** Set default host and port for MSSQL source ([googleapis#1943](googleapis#1943)) ([7a9cc63](googleapis@7a9cc63)) * **tools/cloudsqlpg:** Add CloudSQL PostgreSQL pre-check tool ([googleapis#1722](googleapis#1722)) ([8752e05](googleapis@8752e05)) * **tools/postgres-list-publication-tables:** Add new postgres-list-publication-tables tool ([googleapis#1919](googleapis#1919)) ([f4b1f0a](googleapis@f4b1f0a)) * **tools/postgres-list-tablespaces:** Add new postgres-list-tablespaces tool ([googleapis#1934](googleapis#1934)) ([5ad7c61](googleapis@5ad7c61)) * **tools/spanner-list-graph:** Tool impl + docs + tests ([googleapis#1923](googleapis#1923)) ([a0f44d3](googleapis@a0f44d3)) ### Bug Fixes * Add import for firebirdsql ([googleapis#2045](googleapis#2045)) ([fb7aae9](googleapis@fb7aae9)) * Correct FAQ to mention HTTP tools ([googleapis#2036](googleapis#2036)) ([7b44237](googleapis@7b44237)) * Format BigQuery numeric output as decimal strings ([googleapis#2084](googleapis#2084)) ([155bff8](googleapis@155bff8)) * Set default annotations for tools in code if annotation not provided in yaml ([googleapis#2049](googleapis#2049)) ([565460c](googleapis@565460c)) * **tools/alloydb-postgres-list-tables:** Exclude google_ml schema from list_tables ([googleapis#2046](googleapis#2046)) ([a03984c](googleapis@a03984c)) * **tools/alloydbcreateuser:** Remove duplication of project praram ([googleapis#2028](googleapis#2028)) ([730ac6d](googleapis@730ac6d)) * **tools/mongodb:** Remove `required` tag from the `canonical` field ([googleapis#2099](googleapis#2099)) ([744214e](googleapis@744214e)) --- 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: Wenxin Du <117315983+duwenxin99@users.noreply.github.com> cb4529c
🤖 I have created a release *beep* *boop* --- ## [0.22.0](googleapis/mcp-toolbox@v0.21.0...v0.22.0) (2025-12-04) ### Features * Add allowed-origins flag ([googleapis#1984](googleapis#1984)) ([862868f](googleapis@862868f)) * **tools/postgres:** Add list-query-stats and get-column-cardinality functions ([googleapis#1976](googleapis#1976)) ([9f76026](googleapis@9f76026)) * **tools/spanner:** Add spanner list graphs to prebuiltconfigs ([googleapis#2056](googleapis#2056)) ([0e7fbf4](googleapis@0e7fbf4)) * **prebuilt/cloud-sql:** Add clone instance tool for cloud sql ([googleapis#1845](googleapis#1845)) ([5e43630](googleapis@5e43630)) * **serverless-spark:** Add create_pyspark_batch tool ([1bf0b51](googleapis@1bf0b51)) * **serverless-spark:** Add create_spark_batch tool ([17a9792](googleapis@17a9792)) * Support alternate accessToken header name ([googleapis#1968](googleapis#1968)) ([18017d6](googleapis@18017d6)) * Support for annotations ([googleapis#2007](googleapis#2007)) ([ac21335](googleapis@ac21335)) * **tool/mssql:** Set default host and port for MSSQL source ([googleapis#1943](googleapis#1943)) ([7a9cc63](googleapis@7a9cc63)) * **tools/cloudsqlpg:** Add CloudSQL PostgreSQL pre-check tool ([googleapis#1722](googleapis#1722)) ([8752e05](googleapis@8752e05)) * **tools/postgres-list-publication-tables:** Add new postgres-list-publication-tables tool ([googleapis#1919](googleapis#1919)) ([f4b1f0a](googleapis@f4b1f0a)) * **tools/postgres-list-tablespaces:** Add new postgres-list-tablespaces tool ([googleapis#1934](googleapis#1934)) ([5ad7c61](googleapis@5ad7c61)) * **tools/spanner-list-graph:** Tool impl + docs + tests ([googleapis#1923](googleapis#1923)) ([a0f44d3](googleapis@a0f44d3)) ### Bug Fixes * Add import for firebirdsql ([googleapis#2045](googleapis#2045)) ([fb7aae9](googleapis@fb7aae9)) * Correct FAQ to mention HTTP tools ([googleapis#2036](googleapis#2036)) ([7b44237](googleapis@7b44237)) * Format BigQuery numeric output as decimal strings ([googleapis#2084](googleapis#2084)) ([155bff8](googleapis@155bff8)) * Set default annotations for tools in code if annotation not provided in yaml ([googleapis#2049](googleapis#2049)) ([565460c](googleapis@565460c)) * **tools/alloydb-postgres-list-tables:** Exclude google_ml schema from list_tables ([googleapis#2046](googleapis#2046)) ([a03984c](googleapis@a03984c)) * **tools/alloydbcreateuser:** Remove duplication of project praram ([googleapis#2028](googleapis#2028)) ([730ac6d](googleapis@730ac6d)) * **tools/mongodb:** Remove `required` tag from the `canonical` field ([googleapis#2099](googleapis#2099)) ([744214e](googleapis@744214e)) --- 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: Wenxin Du <117315983+duwenxin99@users.noreply.github.com> cb4529c
🤖 I have created a release *beep* *boop* --- ## [0.22.0](v0.21.0...v0.22.0) (2025-12-04) ### Features * Add allowed-origins flag ([#1984](#1984)) ([862868f](862868f)) * **tools/postgres:** Add list-query-stats and get-column-cardinality functions ([#1976](#1976)) ([9f76026](9f76026)) * **tools/spanner:** Add spanner list graphs to prebuiltconfigs ([#2056](#2056)) ([0e7fbf4](0e7fbf4)) * **prebuilt/cloud-sql:** Add clone instance tool for cloud sql ([#1845](#1845)) ([5e43630](5e43630)) * **serverless-spark:** Add create_pyspark_batch tool ([1bf0b51](1bf0b51)) * **serverless-spark:** Add create_spark_batch tool ([17a9792](17a9792)) * Support alternate accessToken header name ([#1968](#1968)) ([18017d6](18017d6)) * Support for annotations ([#2007](#2007)) ([ac21335](ac21335)) * **tool/mssql:** Set default host and port for MSSQL source ([#1943](#1943)) ([7a9cc63](7a9cc63)) * **tools/cloudsqlpg:** Add CloudSQL PostgreSQL pre-check tool ([#1722](#1722)) ([8752e05](8752e05)) * **tools/postgres-list-publication-tables:** Add new postgres-list-publication-tables tool ([#1919](#1919)) ([f4b1f0a](f4b1f0a)) * **tools/postgres-list-tablespaces:** Add new postgres-list-tablespaces tool ([#1934](#1934)) ([5ad7c61](5ad7c61)) * **tools/spanner-list-graph:** Tool impl + docs + tests ([#1923](#1923)) ([a0f44d3](a0f44d3)) ### Bug Fixes * Add import for firebirdsql ([#2045](#2045)) ([fb7aae9](fb7aae9)) * Correct FAQ to mention HTTP tools ([#2036](#2036)) ([7b44237](7b44237)) * Format BigQuery numeric output as decimal strings ([#2084](#2084)) ([155bff8](155bff8)) * Set default annotations for tools in code if annotation not provided in yaml ([#2049](#2049)) ([565460c](565460c)) * **tools/alloydb-postgres-list-tables:** Exclude google_ml schema from list_tables ([#2046](#2046)) ([a03984c](a03984c)) * **tools/alloydbcreateuser:** Remove duplication of project praram ([#2028](#2028)) ([730ac6d](730ac6d)) * **tools/mongodb:** Remove `required` tag from the `canonical` field ([#2099](#2099)) ([744214e](744214e)) --- 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: Wenxin Du <117315983+duwenxin99@users.noreply.github.com>
🤖 I have created a release *beep* *boop* --- ## [0.22.0](googleapis/mcp-toolbox@v0.21.0...v0.22.0) (2025-12-04) ### Features * Add allowed-origins flag ([googleapis#1984](googleapis#1984)) ([862868f](googleapis@862868f)) * **tools/postgres:** Add list-query-stats and get-column-cardinality functions ([googleapis#1976](googleapis#1976)) ([9f76026](googleapis@9f76026)) * **tools/spanner:** Add spanner list graphs to prebuiltconfigs ([googleapis#2056](googleapis#2056)) ([0e7fbf4](googleapis@0e7fbf4)) * **prebuilt/cloud-sql:** Add clone instance tool for cloud sql ([googleapis#1845](googleapis#1845)) ([5e43630](googleapis@5e43630)) * **serverless-spark:** Add create_pyspark_batch tool ([1bf0b51](googleapis@1bf0b51)) * **serverless-spark:** Add create_spark_batch tool ([17a9792](googleapis@17a9792)) * Support alternate accessToken header name ([googleapis#1968](googleapis#1968)) ([18017d6](googleapis@18017d6)) * Support for annotations ([googleapis#2007](googleapis#2007)) ([ac21335](googleapis@ac21335)) * **tool/mssql:** Set default host and port for MSSQL source ([googleapis#1943](googleapis#1943)) ([7a9cc63](googleapis@7a9cc63)) * **tools/cloudsqlpg:** Add CloudSQL PostgreSQL pre-check tool ([googleapis#1722](googleapis#1722)) ([8752e05](googleapis@8752e05)) * **tools/postgres-list-publication-tables:** Add new postgres-list-publication-tables tool ([googleapis#1919](googleapis#1919)) ([f4b1f0a](googleapis@f4b1f0a)) * **tools/postgres-list-tablespaces:** Add new postgres-list-tablespaces tool ([googleapis#1934](googleapis#1934)) ([5ad7c61](googleapis@5ad7c61)) * **tools/spanner-list-graph:** Tool impl + docs + tests ([googleapis#1923](googleapis#1923)) ([a0f44d3](googleapis@a0f44d3)) ### Bug Fixes * Add import for firebirdsql ([googleapis#2045](googleapis#2045)) ([fb7aae9](googleapis@fb7aae9)) * Correct FAQ to mention HTTP tools ([googleapis#2036](googleapis#2036)) ([7b44237](googleapis@7b44237)) * Format BigQuery numeric output as decimal strings ([googleapis#2084](googleapis#2084)) ([155bff8](googleapis@155bff8)) * Set default annotations for tools in code if annotation not provided in yaml ([googleapis#2049](googleapis#2049)) ([565460c](googleapis@565460c)) * **tools/alloydb-postgres-list-tables:** Exclude google_ml schema from list_tables ([googleapis#2046](googleapis#2046)) ([a03984c](googleapis@a03984c)) * **tools/alloydbcreateuser:** Remove duplication of project praram ([googleapis#2028](googleapis#2028)) ([730ac6d](googleapis@730ac6d)) * **tools/mongodb:** Remove `required` tag from the `canonical` field ([googleapis#2099](googleapis#2099)) ([744214e](googleapis@744214e)) --- 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: Wenxin Du <117315983+duwenxin99@users.noreply.github.com>
🤖 I have created a release *beep* *boop* --- ## [0.22.0](googleapis/mcp-toolbox@v0.21.0...v0.22.0) (2025-12-04) ### Features * Add allowed-origins flag ([#1984](googleapis/mcp-toolbox#1984)) ([862868f](googleapis/mcp-toolbox@862868f)) * **tools/postgres:** Add list-query-stats and get-column-cardinality functions ([#1976](googleapis/mcp-toolbox#1976)) ([9f76026](googleapis/mcp-toolbox@9f76026)) * **tools/spanner:** Add spanner list graphs to prebuiltconfigs ([#2056](googleapis/mcp-toolbox#2056)) ([0e7fbf4](googleapis/mcp-toolbox@0e7fbf4)) * **prebuilt/cloud-sql:** Add clone instance tool for cloud sql ([#1845](googleapis/mcp-toolbox#1845)) ([5e43630](googleapis/mcp-toolbox@5e43630)) * **serverless-spark:** Add create_pyspark_batch tool ([1bf0b51](googleapis/mcp-toolbox@1bf0b51)) * **serverless-spark:** Add create_spark_batch tool ([17a9792](googleapis/mcp-toolbox@17a9792)) * Support alternate accessToken header name ([#1968](googleapis/mcp-toolbox#1968)) ([18017d6](googleapis/mcp-toolbox@18017d6)) * Support for annotations ([#2007](googleapis/mcp-toolbox#2007)) ([ac21335](googleapis/mcp-toolbox@ac21335)) * **tool/mssql:** Set default host and port for MSSQL source ([#1943](googleapis/mcp-toolbox#1943)) ([7a9cc63](googleapis/mcp-toolbox@7a9cc63)) * **tools/cloudsqlpg:** Add CloudSQL PostgreSQL pre-check tool ([#1722](googleapis/mcp-toolbox#1722)) ([8752e05](googleapis/mcp-toolbox@8752e05)) * **tools/postgres-list-publication-tables:** Add new postgres-list-publication-tables tool ([#1919](googleapis/mcp-toolbox#1919)) ([f4b1f0a](googleapis/mcp-toolbox@f4b1f0a)) * **tools/postgres-list-tablespaces:** Add new postgres-list-tablespaces tool ([#1934](googleapis/mcp-toolbox#1934)) ([5ad7c61](googleapis/mcp-toolbox@5ad7c61)) * **tools/spanner-list-graph:** Tool impl + docs + tests ([#1923](googleapis/mcp-toolbox#1923)) ([a0f44d3](googleapis/mcp-toolbox@a0f44d3)) ### Bug Fixes * Add import for firebirdsql ([#2045](googleapis/mcp-toolbox#2045)) ([fb7aae9](googleapis/mcp-toolbox@fb7aae9)) * Correct FAQ to mention HTTP tools ([#2036](googleapis/mcp-toolbox#2036)) ([7b44237](googleapis/mcp-toolbox@7b44237)) * Format BigQuery numeric output as decimal strings ([#2084](googleapis/mcp-toolbox#2084)) ([155bff8](googleapis/mcp-toolbox@155bff8)) * Set default annotations for tools in code if annotation not provided in yaml ([#2049](googleapis/mcp-toolbox#2049)) ([565460c](googleapis/mcp-toolbox@565460c)) * **tools/alloydb-postgres-list-tables:** Exclude google_ml schema from list_tables ([#2046](googleapis/mcp-toolbox#2046)) ([a03984c](googleapis/mcp-toolbox@a03984c)) * **tools/alloydbcreateuser:** Remove duplication of project praram ([#2028](googleapis/mcp-toolbox#2028)) ([730ac6d](googleapis/mcp-toolbox@730ac6d)) * **tools/mongodb:** Remove `required` tag from the `canonical` field ([#2099](googleapis/mcp-toolbox#2099)) ([744214e](googleapis/mcp-toolbox@744214e)) --- 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: Wenxin Du <117315983+duwenxin99@users.noreply.github.com>
Description
This commit allows a tool to pull an alternate authorization
token from the header of the http request.
This is initially being built for the Looker integration. Looker
uses its own OAuth token. When deploying MCP Toolbox to Cloud
Run, the default token in the "Authorization" header is for
authentication with Cloud Run. An alternate token can be put into
another header by a client such as ADK or any other client that
can programatically set http headers. This token will be used
to authenticate with Looker.
If needed, other sources can use this by setting the header name
in the source config, passing it into the tool config, and returning
the header name in the Tool GetAuthTokenHeaderName() function.
PR Checklist
CONTRIBUTING.md
bug/issue
before writing your code! That way we can discuss the change, evaluate
designs, and agree on the general idea
!if this involve a breaking change🛠️ Fixes #1540