feat(tools/dataplex-get-data-product): add dataplex-get-data-product tool (#3499)

> [!IMPORTANT]
> **Stacked Changeset:** This PR depends on changes in previous PRs
(#3337).
> - **Please merge previous PRs first** before reviewing/merging this
one.
> - The file diff below will appear large as it includes its ancestors'
commits. It will resolve itself once the preceding PRs are merged and
this branch is synced.

This PR implements the  dataplex-get-data-product  tool for the Dataplex
(Knowledge Catalog) source, allowing users to retrieve detailed metadata
for
  a specific Data Product.

  Changes overview:

  - Dataplex Source: Implemented  GetDataProduct  to fetch a single Data
Product by location and ID. It maps SDK structures to a clean flat
output,
  including display name, description, owner emails, and access groups.
- New Tool: Created the dataplex-get-data-product tool exposing
locationId
  and  dataProductId  parameters.
  - Tests:
      - Added unit tests for tool configuration parsing.
- Added integration tests verifying successful retrieval of Data
Products
      and proper 401 handling on unauthorized requests.
- Documentation: Created the reference documentation page for the tool,
  updated the Dataplex source guide, and added the tool details to the
  capabilities list.

---------

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Yuan Teoh <45984206+Yuan325@users.noreply.github.com>

Author: 3 people

cmd/internal/config_test.go

@@ -1862,7 +1862,7 @@ func TestPrebuiltTools(t *testing.T) {
 				},
 				"data-products": tools.ToolsetConfig{
 					Name:      "data-products",
-					ToolNames: []string{"search_entries", "lookup_entry", "search_aspect_types", "lookup_context", "list_data_products"},
+					ToolNames: []string{"search_entries", "lookup_entry", "search_aspect_types", "lookup_context", "list_data_products", "get_data_product"},
 				},
 				"enrich": tools.ToolsetConfig{
 					Name:      "enrich",

cmd/internal/imports.go

@@ -164,6 +164,7 @@ import (
 	_ "github.com/googleapis/mcp-toolbox/internal/tools/dataplex/dataplexgeneratedatainsights"
 	_ "github.com/googleapis/mcp-toolbox/internal/tools/dataplex/dataplexgeneratedataprofile"
 	_ "github.com/googleapis/mcp-toolbox/internal/tools/dataplex/dataplexgetdatainsights"
+	_ "github.com/googleapis/mcp-toolbox/internal/tools/dataplex/dataplexgetdataproduct"
 	_ "github.com/googleapis/mcp-toolbox/internal/tools/dataplex/dataplexgetdataprofile"
 	_ "github.com/googleapis/mcp-toolbox/internal/tools/dataplex/dataplexgetdataqualityresults"
 	_ "github.com/googleapis/mcp-toolbox/internal/tools/dataplex/dataplexgetdiscoveryresults"

docs/KNOWLEDGE_CATALOG_README.md

@@ -7,7 +7,8 @@ The Knowledge Catalog (formerly known as Dataplex) Model Context Protocol (MCP)
 An editor configured to use the Knowledge Catalog MCP server can use its AI capabilities to help you:
 
 - **Search Catalog** - Search for entries in Knowledge Catalog
-- **Explore Metadata** - Lookup specific entries and search aspect types
+- **Explore Metadata** - Lookup specific entries, search aspect types, and list/retrieve Data Products
+- **Data Quality** - Search for data quality scans
 
 ## Prerequisites
 
@@ -41,6 +42,8 @@ Once configured, the MCP server will automatically provide Knowledge Catalog cap
 
 *   "Search for entries related to 'sales' in Knowledge Catalog."
 *   "Look up details for the entry 'projects/my-project/locations/us-central1/entryGroups/my-group/entries/my-entry'."
+*   "List all Data Products."
+*   "Get details of the Data Product 'projects/my-project/locations/us-central1/dataProducts/my-product'."
 
 ## Server Capabilities
 
@@ -54,6 +57,7 @@ The Knowledge Catalog MCP server provides the following tools:
 | `lookup_context`      | Retrieve rich metadata regarding one or more data assets along with their relationships.                                     |
 | `search_dq_scans`     | Search for Data Quality scans.                                                                                               |
 | `list_data_products`  | List Data Products for the current project.                                                                                  |
+| `get_data_product`    | Retrieve a specific Data Product.                                                                                            |
 
 ## Custom MCP Server Configuration
 

docs/en/integrations/knowledge-catalog/prebuilt-configs/knowledge-catalog.md

@@ -20,8 +20,9 @@ aliases:
     *   `lookup_entry`: Retrieves a specific entry from Knowledge Catalog.
     *   `search_aspect_types`: Finds aspect types relevant to the query.
     *   `lookup_context`: Retrieves rich metadata regarding one or more data assets along with their relationships.
-    *   `search_dq_scans`: Search for data quality scans in Dataplex.
+    *   `search_dq_scans`: Searches for data quality scans in Dataplex.
     *   `list_data_products`: Lists Data Products across all locations.
+    *   `get_data_product`: Retrieves a specific Data Product.
     *   `generate_data_insights`: Creates a new Dataplex Data Documentation scan template and triggers the run.
     *   `get_data_insights`: Retrieves the final generated data insights for a completed scan.
     *   `generate_data_profile`: Creates a new Dataplex Data Profile scan template and triggers the run.
@@ -34,6 +35,5 @@ aliases:
     *   `get_run_status`: Retrieves the execution status of the latest background job run.
 *   **Toolsets:**
     *   `discovery`: Metadata discovery and search toolset (`search_entries`, `lookup_entry`, `search_aspect_types`, `lookup_context`, `search_dq_scans`).
-    *   `data-products`: Data Products and Data Assets curation and management toolset (`search_entries`, `lookup_entry`, `search_aspect_types`, `lookup_context`, `list_data_products`).
+    *   `data-products`: Data Products and Data Assets curation and management toolset (`search_entries`, `lookup_entry`, `search_aspect_types`, `lookup_context`, `list_data_products`, `get_data_product`).
     *   `enrich`: Metadata enrichment pipeline orchestration and execution toolset (`search_entries`, `lookup_entry`, `lookup_context`, `generate_data_insights`, `get_data_insights`, `generate_data_profile`, `get_data_profile`, `discover_metadata`, `get_discovery_results`, `check_data_quality`, `get_data_quality_results`, `get_operation`, `get_run_status`).
-

docs/en/integrations/knowledge-catalog/source.md

@@ -381,4 +381,11 @@ This abbreviated syntax works for the qualified predicates except for `label` in
 2. You can optionally filter by `display_name` (e.g., "`display_name:\"my-product\"`") or other fields using the Dataplex filter syntax.
 ### Response
 1. Unless asked for a specific data product, respond with all entries returned.
+
+## Tool: get_data_product
+### Request
+1. Use this tool to retrieve detailed metadata for a specific Data Product.
+2. You must provide `locationId` and `dataProductId`.
+### Response
+1. Present the retrieved metadata for the Data Product, including its display name, description, owner emails, asset count, labels, and access groups.
 ```

docs/en/integrations/knowledge-catalog/tools/knowledge-catalog-get-data-product.md

@@ -0,0 +1,68 @@
+---
+title: "dataplex-get-data-product"
+type: docs
+weight: 1
+description: >
+  A "dataplex-get-data-product" tool allows to retrieve a specific Data Product.
+---
+
+## About
+
+A `dataplex-get-data-product` tool retrieves detailed metadata for a specific Data Product in Knowledge Catalog (formerly known as Dataplex).
+
+View the [Data Products guide][guide] for more information.
+
+[guide]: https://docs.cloud.google.com/dataplex/docs/data-products-overview
+
+## Compatible Sources
+
+{{< compatible-sources >}}
+
+## Requirements
+
+### IAM Permissions
+
+Knowledge Catalog uses [Identity and Access Management (IAM)][iam-overview] to control
+user and group access to Knowledge Catalog resources. Toolbox will use your
+[Application Default Credentials (ADC)][adc] to authorize and authenticate when
+interacting with [Knowledge Catalog][dataplex-docs].
+
+In addition to [setting the ADC for your server][set-adc], you need to ensure
+the IAM identity has been given the correct IAM permissions for the tasks you
+intend to perform. See [Knowledge Catalog IAM permissions][iam-permissions]
+and [Knowledge Catalog IAM roles][iam-roles] for more information on
+applying IAM permissions and roles to an identity.
+
+[iam-overview]: https://cloud.google.com/dataplex/docs/iam-and-access-control
+[adc]: https://cloud.google.com/docs/authentication#adc
+[set-adc]: https://cloud.google.com/docs/authentication/provide-credentials-adc
+[iam-permissions]: https://cloud.google.com/dataplex/docs/iam-permissions
+[iam-roles]: https://cloud.google.com/dataplex/docs/iam-roles
+[dataplex-docs]: https://cloud.google.com/dataplex
+
+## Parameters
+
+The `dataplex-get-data-product` tool has the following parameters:
+
+| **field**     | **type** | **required** | **description**                                                 |
+| ------------- | -------- | ------------ | --------------------------------------------------------------- |
+| locationId    | string   | true         | The location ID (e.g. `us`, `us-central1`) of the Data Product. |
+| dataProductId | string   | true         | The unique ID of the Data Product.                              |
+
+## Example
+
+```yaml
+kind: tool
+name: get_data_product
+type: dataplex-get-data-product
+source: my-dataplex-source
+description: Use this tool to retrieve a Data Product.
+```
+
+## Reference
+
+| **field**   | **type** | **required** | **description**                                    |
+| ----------- | -------- | ------------ | -------------------------------------------------- |
+| type        | string   | true         | Must be "dataplex-get-data-product".               |
+| source      | string   | true         | Name of the source the tool should execute on.     |
+| description | string   | true         | Description of the tool that is passed to the LLM. |

docs/en/integrations/knowledge-catalog/tools/knowledge-catalog-list-data-products.md

@@ -10,9 +10,9 @@ description: >
 
 A `dataplex-list-data-products` tool lists all Data Products in Knowledge Catalog (formerly known as Dataplex) across all locations (globally).
 
-View the [Data Products usage guide][usage-guide] for more information.
+View the [Data Products guide][guide] for more information.
 
-[usage-guide]: https://docs.cloud.google.com/dataplex/docs/use-data-products
+[guide]: https://docs.cloud.google.com/dataplex/docs/data-products-overview
 
 ## Compatible Sources
 
@@ -46,7 +46,7 @@ The `dataplex-list-data-products` tool has the following optional parameters:
 
 | **field** | **type** | **required** | **description**                                                                                                                                                                                                                                                |
 | --------- | -------- | ------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| filter    | string   | false        | Filter string to list data products. Based on the AIP-160 proposal. Use '=' for exact, and ':' for contains matching. String literals must be enclosed within "". Matching accross all fields at once is not yet supported. E.g. "display_name:\"my-product\"" |
+| filter    | string   | false        | Filter string to list data products. Based on the AIP-160 proposal. Use '=' for exact, and ':' for contains matching. String literals must be enclosed within "". Matching across all fields at once is not yet supported. E.g. "display_name:\"my-product\"" |
 | pageSize  | integer  | false        | Number of returned data products in the page. Defaults to `10`.                                                                                                                                                                                                |
 | orderBy   | string   | false        | Specifies the ordering of results.                                                                                                                                                                                                                             |
 

internal/prebuiltconfigs/tools/dataplex.yaml

@@ -54,6 +54,12 @@ source: dataplex-source
 description: Lists Data Products across all locations.
 ---
 kind: tool
+name: get_data_product
+type: dataplex-get-data-product
+source: dataplex-source
+description: Retrieves specific metadata regarding a Data Product.
+---
+kind: tool
 name: generate_data_insights
 type: dataplex-generate-data-insights
 source: dataplex-source
@@ -245,6 +251,7 @@ tools:
 - search_aspect_types
 - lookup_context
 - list_data_products
+- get_data_product
 ---
 kind: toolset
 name: enrich

internal/sources/dataplex/dataplex.go

@@ -372,7 +372,7 @@ func (s *Source) ListDataProducts(
 	pageSize int,
 	orderBy string,
 ) ([]*DataProductSummary, error) {
-	if s.dataProductClient == nil {
+	if s.GetDataProductClient() == nil {
 		return nil, fmt.Errorf("dataplex data product client is not initialized")
 	}
 	if pageSize <= 0 {
@@ -386,7 +386,7 @@ func (s *Source) ListDataProducts(
 		OrderBy:  orderBy,
 	}
 
-	it := s.dataProductClient.ListDataProducts(ctx, req)
+	it := s.GetDataProductClient().ListDataProducts(ctx, req)
 	var results []*DataProductSummary
 
 	for len(results) < pageSize {
@@ -401,14 +401,14 @@ func (s *Source) ListDataProducts(
 			return nil, fmt.Errorf("failed to list data products: %w", err)
 		}
 		parts := strings.Split(dp.GetName(), "/")
-		var locationId, dataProductId string
+		var locID, prodID string
 		if len(parts) >= 6 && parts[0] == "projects" && parts[2] == "locations" && parts[4] == "dataProducts" {
-			locationId = parts[3]
-			dataProductId = parts[5]
+			locID = parts[3]
+			prodID = parts[5]
 		}
 		results = append(results, &DataProductSummary{
-			LocationID:    locationId,
-			DataProductID: dataProductId,
+			LocationID:    locID,
+			DataProductID: prodID,
 			DisplayName:   dp.GetDisplayName(),
 			OwnerEmails:   dp.GetOwnerEmails(),
 			AssetCount:    dp.GetAssetCount(),
@@ -417,6 +417,68 @@ func (s *Source) ListDataProducts(
 	return results, nil
 }
 
+type AccessGroup struct {
+	ID             string `json:"id"`
+	DisplayName    string `json:"displayName"`
+	Description    string `json:"description"`
+	GoogleGroup    string `json:"googleGroup,omitempty"`
+	ServiceAccount string `json:"serviceAccount,omitempty"`
+}
+
+type DataProduct struct {
+	LocationID    string            `json:"locationId"`
+	DataProductID string            `json:"dataProductId"`
+	DisplayName   string            `json:"displayName"`
+	Description   string            `json:"description"`
+	OwnerEmails   []string          `json:"ownerEmails"`
+	AssetCount    int32             `json:"assetCount"`
+	Labels        map[string]string `json:"labels"`
+	AccessGroups  []AccessGroup     `json:"accessGroups"`
+}
+
+func (s *Source) GetDataProduct(ctx context.Context, locationID string, dataProductID string) (*DataProduct, error) {
+	if s.GetDataProductClient() == nil {
+		return nil, fmt.Errorf("dataplex data product client is not initialized")
+	}
+	name := fmt.Sprintf("projects/%s/locations/%s/dataProducts/%s", s.ProjectID(), locationID, dataProductID)
+	req := &dataplexpb.GetDataProductRequest{
+		Name: name,
+	}
+	resp, err := s.GetDataProductClient().GetDataProduct(ctx, req)
+	if err != nil {
+		return nil, err
+	}
+
+	accessGroups := []AccessGroup{}
+	for _, ag := range resp.GetAccessGroups() {
+		accessGroups = append(accessGroups, AccessGroup{
+			ID:             ag.GetId(),
+			DisplayName:    ag.GetDisplayName(),
+			Description:    ag.GetDescription(),
+			GoogleGroup:    ag.GetPrincipal().GetGoogleGroup(),
+			ServiceAccount: ag.GetPrincipal().GetServiceAccount(),
+		})
+	}
+
+	parts := strings.Split(resp.GetName(), "/")
+	var locID, prodID string
+	if len(parts) >= 6 && parts[0] == "projects" && parts[2] == "locations" && parts[4] == "dataProducts" {
+		locID = parts[3]
+		prodID = parts[5]
+	}
+
+	return &DataProduct{
+		LocationID:    locID,
+		DataProductID: prodID,
+		DisplayName:   resp.GetDisplayName(),
+		Description:   resp.GetDescription(),
+		OwnerEmails:   resp.GetOwnerEmails(),
+		AssetCount:    resp.GetAssetCount(),
+		Labels:        resp.GetLabels(),
+		AccessGroups:  accessGroups,
+	}, nil
+}
+
 func (s *Source) GenerateDataInsights(ctx context.Context, location, resourcePath string, publish bool) (string, error) {
 	parent := fmt.Sprintf("projects/%s/locations/%s", s.ProjectID(), location)
 	dataScanID := fmt.Sprintf("nq-doc-%s", uuid.New().String())