The `ParseParams` Tool interface is only passing the tool's parameter
into a generic `parameters.ParseParams()` helper. Instead of keeping it
as a tool interface, we add a `GetParameters()` method
(https://github.com/googleapis/genai-toolbox/pull/2374) to the tool
interface and call it directly from the API handlers. This way we keep
the parameter parsing logic independent from the tools.
This PR introduces a significant update to the Toolbox configuration
file format, which is one of the primary **breaking changes** required
for the implementation of the Advanced Control Plane.
# Summary of Changes
The configuration schema has been updated to enforce resource isolation
and facilitate atomic, incremental updates.
* Resource Isolation: Resource definitions are now separated into
individual blocks, using a distinct structure for each resource type
(Source, Tool, Toolset, etc.). This improves readability, management,
and auditing of configuration files.
* Field Name Modification: Internal field names have been modified to
align with declarative methodologies. Specifically, the configuration
now separates kind (general resource type, e.g., Source) from type
(specific implementation, e.g., Postgres).
# User Impact
Existing tools.yaml configuration files are now in an outdated format.
Users must eventually update their files to the new YAML format.
# Mitigation & Compatibility
Backward compatibility is maintained during this transition to ensure no
immediate user action is required for existing files.
* Immediate Backward Compatibility: The source code includes a
pre-processing layer that automatically detects outdated configuration
files (v1 format) and converts them to the new v2 format under the hood.
* [COMING SOON] Migration Support: The new toolbox migrate subcommand
will be introduced to allow users to automatically convert their old
configuration files to the latest format.
# Example
Example for config file v2:
```
kind: sources
name: my-pg-instance
type: cloud-sql-postgres
project: my-project
region: my-region
instance: my-instance
database: my_db
user: my_user
password: my_pass
---
kind: authServices
name: my-google-auth
type: google
clientId: testing-id
---
kind: tools
name: example_tool
type: postgres-sql
source: my-pg-instance
description: some description
statement: SELECT * FROM SQL_STATEMENT;
parameters:
- name: country
type: string
description: some description
---
kind: tools
name: example_tool_2
type: postgres-sql
source: my-pg-instance
description: returning the number one
statement: SELECT 1;
---
kind: toolsets
name: example_toolset
tools:
- example_tool
```
---------
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Averi Kitsch <akitsch@google.com>
Add parameter `embeddedBy` field to support vector embedding & semantic
search.
Major change in `internal/util/parameters/parameters.go`
This PR only adds vector formatter for the postgressql tool. Other tools
requiring vector formatting may not work with embeddedBy.
Second part of the Semantic Search support. First part:
https://github.com/googleapis/genai-toolbox/pull/2121
Move source-related queries from `Invoke()` function into Source.
The following sources are updated in this PR:
* mindsdb
* oceanbase
* oracle
* redis
* singlestore
* cloudmonitoring
This is an effort to generalizing tools to work with any Source that
implements a specific interface. This will provide a better segregation
of the roles for Tools vs Source.
Tool's role will be limited to the following:
* Resolve any pre-implementation steps or parameters (e.g. template
parameters)
* Retrieving Source
* Calling the source's implementation
* reduce oracle integration test coverage to 20%. There's no code change
or test reduction in this PR. It might be because the Invoke() function
was dedupe, hence the total line covered is reduced.
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()`).
## 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
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
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.
🚀 Add MindsDB Integration: Expand Toolbox to Hundreds of Datasources
Overview
This PR introduces comprehensive MindsDB integration to the Google GenAI
Toolbox, enabling SQL queries across hundreds of datasources through a
unified interface. MindsDB is the most widely adopted AI federated
database that automatically translates MySQL queries into REST APIs,
GraphQL, and native protocols.
🎯 Key Value for Google GenAI Toolbox Ecosystem
1. Massive Datasource Expansion
Before: Toolbox limited to ~15 traditional databases
After: Access to hundreds of datasources including Salesforce, Jira,
GitHub, MongoDB, Gmail, Slack, and more
Impact: Dramatically expands the toolbox's reach and utility for
enterprise users
2. Cross-Datasource Analytics
New Capability: Perform joins and analytics across different datasources
seamlessly
Example: Join Salesforce opportunities with GitHub activity to correlate
sales with development activity
Value: Enables comprehensive data analysis that was previously
impossible
3. API Abstraction Layer
Innovation: Write standard SQL queries that automatically translate to
any API
Benefit: Developers can query REST APIs, GraphQL, and native protocols
using familiar SQL syntax
Impact: Reduces complexity and learning curve for accessing diverse
datasources
4. ML Model Integration
Enhanced Capability: Use ML models as virtual tables for real-time
predictions
Example: Query customer churn predictions directly through SQL
Value: Brings AI/ML capabilities into the standard SQL workflow
🔧 Technical Implementation
Source Layer
✅ New MindsDB source implementation using MySQL wire protocol
✅ Comprehensive test coverage with integration tests
✅ Updated existing MySQL tools to support MindsDB sources
✅ Created dedicated MindsDB tools for enhanced functionality
Tools Layer
✅ mindsdb-execute-sql: Direct SQL execution across federated datasources
✅ mindsdb-sql: Parameterized SQL queries with template support
✅ Backward compatibility with existing MySQL tools
Documentation & Configuration
✅ Comprehensive documentation with real-world examples
✅ Prebuilt configuration for easy setup
✅ Updated CLI help text and command-line options
📊 Supported Datasources
Business Applications
Salesforce (leads, opportunities, accounts)
Jira (issues, projects, workflows)
GitHub (repositories, commits, PRs)
Slack (channels, messages, teams)
HubSpot (contacts, companies, deals)
Databases & Storage
MongoDB (NoSQL collections as structured tables)
Redis (key-value stores)
Elasticsearch (search and analytics)
S3, filesystems, etc (file storage)
Communication & Email
Gmail/Outlook (emails, attachments)
Microsoft Teams (communications, files)
Discord (server data, messages)
🎯 Example Use Cases
Cross-Datasource Analytics
-- Join Salesforce opportunities with GitHub activity
```
SELECT
s.opportunity_name,
s.amount,
g.repository_name,
COUNT(g.commits) as commit_count
FROM salesforce.opportunities s
JOIN github.repositories g ON s.account_id = g.owner_id
WHERE s.stage = 'Closed Won';
```
Email & Communication Analysis
```
-- Analyze email patterns with Slack activity
SELECT
e.sender,
e.subject,
s.channel_name,
COUNT(s.messages) as message_count
FROM gmail.emails e
JOIN slack.messages s ON e.sender = s.user_name
WHERE e.date >= '2024-01-01';
```
🚀 Benefits for Google GenAI Toolbox
Enterprise Adoption: Enables access to enterprise datasources
(Salesforce, Jira, etc.)
Developer Productivity: Familiar SQL interface for any datasource
AI/ML Integration: Seamless integration of ML models into SQL workflows
Scalability: Single interface for hundreds of datasources
Competitive Advantage: Unique federated database capabilities in the
toolbox ecosystem
📈 Impact Metrics
Datasource Coverage: +1000% increase in supported datasources
API Abstraction: Eliminates need to learn individual API syntaxes
Cross-Platform Analytics: Enables previously impossible data
correlations
ML Integration: Brings AI capabilities into standard SQL workflows
🔗 Resources
MindsDB Documentation
MindsDB GitHub
Updated Toolbox Documentation
✅ Testing
✅ Unit tests for MindsDB source implementation
✅ Integration tests with real datasource examples
✅ Backward compatibility with existing MySQL tools
✅ Documentation examples tested and verified
This integration transforms the Google GenAI Toolbox from a traditional
database tool into a comprehensive federated data platform, enabling
users to query and analyze data across their entire technology stack
through a unified SQL interface.
---------
Co-authored-by: duwenxin <duwenxin@google.com>
Co-authored-by: setohe0909 <setohe.09@gmail.com>
Co-authored-by: Kurtis Van Gent <31518063+kurtisvg@users.noreply.github.com>
Co-authored-by: Wenxin Du <117315983+duwenxin99@users.noreply.github.com>
Co-authored-by: Yuan Teoh <45984206+Yuan325@users.noreply.github.com>
