This PR update the linking mechanism between Source and Tool.
Tools are directly linked to their Source, either by pointing to the
Source's functions or by assigning values from the source during Tool's
initialization. However, the existing approach means that any
modification to the Source after Tool's initialization might not be
reflected. To address this limitation, each tool should only store a
name reference to the Source, rather than direct link or assigned
values.
Tools will provide interface for `compatibleSource`. This will be used
to determine if a Source is compatible with the Tool.
```
type compatibleSource interface{
Client() http.Client
ProjectID() string
}
```
During `Invoke()`, the tool will run the following operations:
* retrieve Source from the `resourceManager` with source's named defined
in Tool's config
* validate Source via `compatibleSource interface{}`
* run the remaining `Invoke()` function. Fields that are needed is
retrieved directly from the source.
With this update, resource manager is also added as input to other
Tool's function that require access to source (e.g.
`RequiresClientAuthorization()`).
This pull request resolves the issue by changing the validation logic
for the spanner-list-graphs tool to prevent server crashes on PostgreSQL
dialects.
The spanner-list-graphs tool currently supports only the GoogleSQL
dialect. Previously, this check was enforced during initialization,
causing the entire server to crash on startup when connected to a
PostgreSQL-dialect database.
**Changes Implemented**
- The modification is in
internal/tools/spanner/spannerlistgraphs/spannerlistgraphs.go.
- Removed the dialect validation from the Initialize method (startup).
- Added the dialect validation to the Invoke method (runtime).
This change ensures the tool initializes successfully regardless of the
dialect, allowing the server to start. It now returns a graceful error
message only if a user explicitly attempts to execute the tool on an
unsupported dialect.
**Validation Process**
Validated changes by running the toolbox locally against a Spanner
instance using the PostgreSQL dialect.
CLI Configuration: Ran the server using the standard Spanner prebuilt
set: go run . --prebuilt spanner --ui
Testing: Confirmed the logic by testing two scenarios
1. PostgreSQL Dialect (Graceful Failure)
Set SPANNER_DIALECT="postgresql".
Result: The server started successfully without crashing (fixing the
bug). When running the spanner-list-graphs tool in the UI, it returned a
clear error message: "operation not supported: The 'spanner-list-graphs'
tool is only available for GoogleSQL dialect databases."
<img width="2171" height="462" alt="Screenshot 2025-12-10 11 24 53 PM"
src="https://github.com/user-attachments/assets/c57e64e4-ddce-42a2-998d-b291d77b7d1d"
/>
<img width="2233" height="971" alt="Screenshot 2025-12-10 11 22 53 PM"
src="https://github.com/user-attachments/assets/8e510a72-4598-4d55-a175-bf9e2f85489d"
/>
<img width="2233" height="971" alt="Screenshot 2025-12-10 11 23 26 PM"
src="https://github.com/user-attachments/assets/a904a45f-25be-42ef-9d5a-a7975cc03a44"
/>
2. GoogleSQL Dialect (Success)
Set SPANNER_DIALECT="googlesql".
Result: The tool executed successfully and returned the graph schema (or
empty results), confirming that normal functionality is preserved.
<img width="2171" height="572" alt="Screenshot 2025-12-10 11 26 59 PM"
src="https://github.com/user-attachments/assets/d9c6c677-cb38-4343-be39-d542439685c4"
/>
<img width="2250" height="938" alt="Screenshot 2025-12-10 11 27 32 PM"
src="https://github.com/user-attachments/assets/6e8f3628-8079-4c99-993a-7ada02a124b0"
/>
<img width="2250" height="938" alt="Screenshot 2025-12-10 11 27 45 PM"
src="https://github.com/user-attachments/assets/a3091228-d73a-44a0-acd2-e7fb463de4e2"
/>
🛠️Fixes#2136
Co-authored-by: Averi Kitsch <akitsch@google.com>
## Description
Return empty list instead of null in list tables tools when no tables
found
## PR Checklist
- [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#2027
---------
Co-authored-by: Averi Kitsch <akitsch@google.com>
## Description
Adds spanner list graphs to prebuildconfigs
## PR Checklist
- [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#2051
---------
Co-authored-by: Averi Kitsch <akitsch@google.com>
## Description
Tool `invoke()` and `RequiresClientAuthorization()` takes a new input
argument -- Resource Manager. Resource manager will be used to retrieve
Source in the next step.
In order to achieve the goal, this PR implements the follows:
* move resource manager from the server package to a new package to
prevent import cycles (between server and mcp)
* added a new interface in `tools.go` to prevent import cycle (between
resources and tools package)
* add new input argument in all tools
## 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
## Description
The MCP spec supports tool annotations like the below structure in the
2025-06-18 version of the spec.
https://modelcontextprotocol.io/specification/2025-06-18/schema#toolannotations
```
{
destructiveHint?: boolean;
idempotentHint?: boolean;
openWorldHint?: boolean;
readOnlyHint?: boolean;
}
```
Added a ToolAnnotations structure, an Annotations member to the
McpManifest structure, and a nil initializer for the Annotations member
to all calls to GetMcpManifest.
The ToolAnnotations structure and the member annotations are all defined
as pointers so that they are omited when not set. There are times when
the zero value is meaningful so this was the only way to make sure that
we distinguish between not setting the annotation and setting it with a
zero value.
## 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#927
---------
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
## Description
Spanner List Graphs tool, similar to list tables it can be used to get
all/specific graph details
## PR Checklist
- [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#1916
---------
Co-authored-by: Averi Kitsch <akitsch@google.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
> 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
## Description
Unmarshal object_details json string into map to make response have
nested json in spannerlisttables instead of nested JSON string
## PR Checklist
- [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#1838
---------
Co-authored-by: Averi Kitsch <akitsch@google.com>
To keep a persistent backend storage for configuration, we will have to
keep a single source of truth. This involves supporting bi-directional
conversion between Config and Tool.
This PR make the following changes:
* Embed Config in Tool
* Add `ToConfig()` to extract Config from Tool.
Jules PR
---
*PR created automatically by Jules for task
[11947649751737965380](https://jules.google.com/task/11947649751737965380)*
---------
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: Yuan Teoh <yuanteoh@google.com>
To facilitate the transition of moving invocation implementation to
Source, we will have to move parameter to `internal/util`. This approach
is crucial because certain parameters may not be fully resolvable
pre-implementation. Since both `internal/sources` and `internal/tools`
will need access to `parameters`, it will be more relevant to move
parameters implementation to utils.
This commit introduces a new `orderedmap` package to preserve the column
order of SQL query results when they are marshaled to JSON.
The default Go `json.Marshal` function sorts map keys, which was causing
the column order to be lost in the output of the database tools.
This commit updates the following tools to use the new `orderedmap`
package:
- `mysqlexecutesql`
- `mssqlexecutesql`
- `postgresexecutesql`
- `spannerexecutesql`
- `sqliteexecutesql`
- `bigqueryexecutesql`
A new test has been added to the `mysqlexecutesql` tool to verify that
the column order is preserved.
## Description
> Should include a concise description of the changes (bug or feature),
it's
> impact, along with a summary of the solution
## 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
🛠️Fixes#1492
---------
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: Yuan Teoh <yuanteoh@google.com>
Co-authored-by: Yuan Teoh <45984206+Yuan325@users.noreply.github.com>
## Description
The debug context logger does not take in value placeholders. The
statements must be first converted to a string.
## 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
🛠️ Fixes #<issue_number_goes_here>
Add `_meta` for `tools/list` method in MCP Toolbox.
If there are authorized invocation, the following will be return in
`_meta`:
```
{
"name":"my-tool-name",
"description":"my tool description",
"inputSchema":{
"type":"object",
"properties":{
"user_id":{"type":"string","description":"user's name from google login"}
},
"required":["user_id"]
},
"_meta":{
"toolbox/authParam":{"user_id":["my_auth"]}
}
}
```
If there are authenticated parameter, the following will be return in
`_meta`:
```
{
"name":"my-tool-name",
"description":"my tool description",
"inputSchema":{
"type":"object",
"properties":{
"sql":{"type":"string","description":"The sql to execute."}
},
"required":["sql"]
},
"_meta":{
"toolbox/authInvoke":["my_auth"]
}
}
```
If there are no authorized invocation or authenticated prameter, the
`_meta` field will be omitted.
With this feature, the following were updated in the source code:
* In each `func(p CommonParameter) McpManifest()`, we will return a
`[]string` for the list of authenticated parameters. This is similar to
how Manifest() return the list of authNames in non-MCP Toolbox's
manifest.
* The `func(ps Parameters) McpManifest()` will return a
`map[string][]string` that with key as param's name, and value as the
param's auth.
* Added a new function `GetMcpManifest()` in `tools.go`. This function
will consctruct the McpManifest, and add the `Metadata` field.
* Associated tests were added or updated.
## Description
This PR introduces a new tool `spanner-list-tables` and includes
comprehensive tests and documentation.
### Features
- __New Tool__: Adds the `spanner-list-tables` tool, which lists tables
in a Spanner database.
- __Dialect-aware__: The tool automatically detects whether the Spanner
database is using the `GoogleSQL` or `PostgreSQL` dialect and executes
the appropriate query.
- __Refactoring__: The integration tests for the new tool have been
refactored to improve maintainability and reduce code duplication by
using shared helper functions.
- __Simpler Prebuilt tool__: The spanner pre-built tool uses this tool
Example tool usage:
```
list_tables:
kind: spanner-list-tables
source: spanner-source
description: "Lists detailed schema information (object type, columns, constraints, indexes) as JSON for user-created tables (ordinary or partitioned). Filters by a comma-separated list of names. If names are omitted, lists all tables in user schemas."
```
## 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
---------
Co-authored-by: Averi Kitsch <akitsch@google.com>
Update `tool.Invoke()` to return type `any` instead of `[]any`.
Toolbox return a map with the `results` key, and the SDK reads the
string from the key. So this won't break existing SDK implementation.
Fixes#870
- Spanner: convert array to typed before querying, as Spanner does not
accept non-typed array []any
- BigQuery: fix https://github.com/googleapis/genai-toolbox/issues/793
- Bigtable: add the required `ElemType` for array-type params
- Redis/Valkey: change indexing to append to avoid extra spaces
Add integration tests for array parameters, skipped for the sources not
supporting arrays:
- SQLite
- Cloud SQL MSSQL
- Cloud SQL MySQL
- MSSQL
- MySQL
Add `templateParameters` to support non-filter parameters and DDL
statements.
Added a new argument `ignoreDdl` at integration test. Admin client is
needed to execute ddl statement in spanner. Toolbox does not use admin
client.
Part of #535
This PR refactors the tool configuration and loading mechanism to use a
dynamic registration pattern. Each tool package now registers itself
with a central registry, and the server configuration code uses this
registry to decode and initialize tools.
Key changes:
- Introduced tools.Register and tools.DecodeToolConfig for dynamic tool
handling.
- Removed direct imports of specific tool packages from
internal/server/config.go.
- Updated individual tool packages to include init() functions for
self-registration.
- Modified ToolKind constants to be local kind constants within each
tool package.
- Adjusted test files to reflect the changes in tool kind identifiers.
This change simplifies adding new tools and decouples the server
configuration from specific tool implementations.
---------
Co-authored-by: Yuan Teoh <yuanteoh@google.com>
Co-authored-by: Yuan <45984206+Yuan325@users.noreply.github.com>
Allowing user to add `readOnly` field in spanner tools.
The existing tool doesn't work for reading schema tables since schema
tables can only be accessed through read-only transaction.
This PR also resolve#435 for Spanner tool.
---------
Co-authored-by: Yuan <45984206+Yuan325@users.noreply.github.com>
This PR is to remove the `NewGenericTool` function within tools.
This function was previously added when we are trying to consolidate the
three postgres tools. However, since we merged it into a single
`postgressql` tool, these functions are not used anymore.
Rename existing `authSource` to `authService` through deprecation.
`AuthService` more clearly distinguishes it from `Sources` objects.
`authSources` will be converted into `authServices` after the
unmarshalling process. A warning log is shown if `authSources` are used
(for both within tools parameters and defining auth services):
```
2025-02-20T13:57:51.156025-08:00 WARN "`authSources` is deprecated, use `authServices` for parameters instead"
2025-02-20T13:57:51.156569-08:00 WARN "`authSources` is deprecated, use `authServices` instead"
2025-02-20T13:57:52.047584-08:00 INFO "Initialized 1 sources."
...
```
The manifest generated will continue to use `authSources` to keep
compatibility with the sdks:
```
{
"serverVersion":"0.1.0",
"tools":{
"test_tool2":{
"description":"Use this tool to test\n",
"parameters":[{
"name":"user_id",
"type":"string",
"description":"Auto-populated from Google login",
"authSources":["my-google-auth"]
}]
}
}
}
```
Test cases with `authSources` are kept for compatibility. Will be
removed when `authSources` are no longer supported.
This only checks within `SourceConfig`, `ToolConfig`, and
`AuthSourceConfig`.
Error when an unknown field is provided:
`2025-01-27T22:43:46.988401-08:00 ERROR "unable to parse tool file at
\"tools.yaml\": unable to parse as \"cloud-sql-postgres\": [2:1] unknown
field \"extra\"\n 1 | database: test_database\n> 2 | extra: here\n ^\n 3
| instance: toolbox-cloudsql\n 4 | kind: cloud-sql-postgres\n 5 |
password: postgres\n 6 | "`
Error when a required field is not provided:
`2025-01-27T17:49:47.584846-08:00 ERROR "unable to parse tool file at
\"tools.yaml\": validation failed: Key: 'Config.Region' Error:Field
validation for 'Region' failed on the 'required' tag"`
---------
Co-authored-by: Kurtis Van Gent <31518063+kurtisvg@users.noreply.github.com>
Add CloudSQL for MySQL source and tool.
CloudSQLMySQL source is initialize with the following config:
```
sources:
my-cloudsqlmysql-source:
kind: cloud-sql-mysql
project: my-project-name
region: my-region
instance: my-instance-name
user: my_user
password: my_pass
database: my_db
# ipType: public # The default dialect is public.
```
MySQL tool is initialize with the following config.
```
tools:
test_tool:
kind: mysql
source: my-cloudsqlmysql-source
description: >
Testing tool.
statement: "SELECT 1;"
```
1. Add []ParamAuthSource to every Parameter type implementation to
support authenticated configs. Create new constructors for types with
auth.
2. Tool invocation API changes to parse auth header and authentecated
parameters.
3. Add authSources to Tool manifest.
Add Spanner source and tool.
Spanner source is initialize with the following config:
```
sources:
my-spanner-source:
kind: spanner
project: my-project-name
instance: my-instance-name
database: my_db
# dialect: postgresql # The default dialect is google_standard_sql.
```
Spanner tool (with gsql dialect) is initialize with the following
config.
```
tools:
get_flight_by_id:
kind: spanner
source: my-cloud-sql-source
description: >
Use this tool to list all airports matching search criteria. Takes
at least one of country, city, name, or all and returns all matching
airports. The agent can decide to return the results directly to
the user.
statement: "SELECT * FROM flights WHERE id = @id"
parameters:
- name: id
type: int
description: 'id' represents the unique ID for each flight.
```
Spanner tool (with postgresql dialect) is initialize with the following
config.
```
tools:
get_flight_by_id:
kind: spanner
source: my-cloud-sql-source
description: >
Use this tool to list all airports matching search criteria. Takes
at least one of country, city, name, or all and returns all matching
airports. The agent can decide to return the results directly to
the user.
statement: "SELECT * FROM flights WHERE id = $1"
parameters:
- name: id
type: int
description: 'id' represents the unique ID for each flight.
```
Note: the only difference in config for both dialects is the sql
statement.
---------
Co-authored-by: Kurtis Van Gent <31518063+kurtisvg@users.noreply.github.com>
