You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
"description": "This plugin provides a specialized suite of skills for data engineers and database practitioners working on Google Cloud. It acts as an expert assistant, allowing you to use natural language prompts in your preferred coding agent to architect complex data pipelines, transform data with dbt, write Spark and BigQuery SQL notebooks, and orchestrate end-to-end workflows across GCP's data ecosystem."
Copy file name to clipboardExpand all lines: .claude-plugin/plugin.json
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -1,5 +1,5 @@
1
1
{
2
-
"name": "data-cloud-ai-dev-kit",
2
+
"name": "data-agent-kit-starter-pack",
3
3
"version": "0.1.8",
4
4
"description": "This plugin provides a specialized suite of skills for data engineers and database practitioners working on Google Cloud. It acts as an expert assistant, allowing you to use natural language prompts in your preferred coding agent to architect complex data pipelines, transform data with dbt, write Spark and BigQuery SQL notebooks, and orchestrate end-to-end workflows across GCP's data ecosystem.",
Copy file name to clipboardExpand all lines: .codex-plugin/plugin.json
+3-3Lines changed: 3 additions & 3 deletions
Original file line number
Diff line number
Diff line change
@@ -1,11 +1,11 @@
1
1
{
2
-
"name": "data-cloud-ai-dev-kit",
2
+
"name": "data-agent-kit-starter-pack",
3
3
"version": "0.1.8",
4
4
"description": "This plugin provides a specialized suite of skills for data engineers and database practitioners working on Google Cloud. It acts as an expert assistant, allowing you to use natural language prompts in your preferred coding agent to architect complex data pipelines, transform data with dbt, write Spark and BigQuery SQL notebooks, and orchestrate end-to-end workflows across GCP's data ecosystem.",
Copy file name to clipboardExpand all lines: README.md
+41-20Lines changed: 41 additions & 20 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,19 +1,19 @@
1
-
# Data Cloud AI Dev Kit
1
+
# Data Agent Kit Starter Pack
2
2
3
3
> [!NOTE]
4
4
> This extension is currently in beta (pre-v1.0), and may see breaking changes until the first stable release (v1.0).
5
5
6
-
This plugin provides a specialized suite of skills and MCP tools for data engineers and database practitioners working on Google Cloud. It acts as an expert assistant, allowing you to use natural language prompts in your preferred coding agent to architect complex data pipelines, transform data with dbt, write Spark and BigQuery SQL notebooks, and orchestrate end-to-end workflows across GCP's data ecosystem (BigQuery, Spanner, BigLake, Dataproc, etc.).
6
+
This plugin provides a specialized suite of skills and MCP tools for data engineers and database practitioners working on Google Cloud. It acts as an expert assistant, allowing you to use natural language prompts in your preferred coding agent to architect complex data pipelines, transform data with dbt, write Spark and BigQuery SQL notebooks, and orchestrate end-to-end workflows across the Google Cloud data ecosystem (BigQuery, Spanner, BigLake, Dataproc, etc.).
7
7
8
8
> [!IMPORTANT]
9
9
> **We Want Your Feedback!**
10
10
> Please share your thoughts with us by opening an issue on GitHub. Your input is invaluable and helps us improve the project for everyone.
11
11
12
-
## Why Use the Data Cloud AI Dev Kit?
12
+
## Why Use the Data Agent Kit Starter Pack?
13
13
14
-
***Seamless Workflow:**Brings Google Cloud data engineering expertise directly into your terminal or IDE via Gemini CLI, Claude Code, or Codex.
15
-
***End-to-End Data Pipelines:** Effortlessly generate code that reads raw data from GCS, processes it with Spark or BigQuery, transforms it through medallion architectures (bronze, silver, gold) using dbt, and exports it to serving layers like Cloud Spanner.
16
-
***Ecosystem Integration:** Work across boundaries—generate BigLake Iceberg catalog tables, train BigQuery ML models (XGBoost, KMEANS), and create interactive Streamlit dashboards or LookML models all from natural language.
14
+
***Seamless Workflow:**Bring Google Cloud data engineering expertise directly into your terminal or IDE via Gemini CLI, Claude Code, or Codex.
15
+
***End-to-End Data Pipelines:** Effortlessly generate code that reads raw data from Cloud Storage, processes it with Spark or BigQuery, transform it through medallion architectures (bronze, silver, gold) using dbt, and export it to serving layers like Spanner.
16
+
***Ecosystem Integration:** Work across boundaries—generate BigLake Iceberg catalog tables, train BigQuery ML models (XGBoost, KMEANS), and create interactive Streamlit dashboards or LookML models, all from natural language.
17
17
***Workflow Orchestration:** Automatically create and schedule orchestration pipelines that tie your notebooks and dbt models together into robust, scheduled jobs.
18
18
19
19
## Prerequisites
@@ -29,30 +29,51 @@ Ensure you have the following installed:
29
29
30
30
### Installation
31
31
32
-
Choose the installation method for your preferred coding agent.
32
+
Choose the installation method for your preferred coding agent. Run the commands in terminal
After running the installation script, run the `codex` command to start the agent, then run:
60
+
61
+
```bash
62
+
/plugins
63
+
```
64
+
65
+
Use the interactive options to install the extension with the name `Data Agent Kit Starter Pack`.
66
+
67
+
## Configure
68
+
69
+
MCP toolboxes are added to the respective agent configuration files. You must configure the MCP toolboxes in your agent's configuration files for them to start successfully:
70
+
71
+
***Gemini CLI and Google Code Assist**: `~/.gemini/extensions/data-agent-kit-starter-pack/gemini-extension.json`
72
+
***Claude Code**: `~/.claude/plugins/cache/data-agent-kit-starter-pack-marketplace/data-agent-kit-starter-pack/<version>/.mcp.json`. After updating, run `/plugin marketplace add https://github.com/gemini-cli-extensions/data-agent-kit-starter-pack` and `/plugin install data-agent-kit-starter-pack@data-agent-kit-starter-pack-marketplace` again.
73
+
***Codex**: `~/.agents/plugins/data-agent-kit-starter-pack/.mcp.json`. After updating, run `/plugins` and use interactive options to uninstall and install `Data Agent Kit Starter Pack` again.
74
+
75
+
In all cases, you must restart the agent after updating the configuration files.
76
+
56
77
## Usage Examples
57
78
58
79
Interact with your coding agent using natural language prompts to perform complex data engineering tasks:
@@ -79,11 +100,11 @@ Interact with your coding agent using natural language prompts to perform comple
79
100
80
101
## Security Reminder: Agent Environment Hardening
81
102
82
-
Your agent has the power to
83
-
execute tools and commands on your behalf. Protect your GCP resources by
84
-
enforcing **Strict Least Privilege** across all CLIs, MCP servers and other
85
-
resources available to your agents. For example, use scoped Service Accounts
for tasks accessing your cloud resources and conducting regular permission and
89
-
agent settings audits to minimize your attack surface.
103
+
Your agent has the power to execute tools and commands on your behalf. Protect your GCP resources by enforcing **Strict Least Privilege** across all CLIs, MCP servers and other resources available to your agents.
104
+
105
+
* Use [service accounts](https://docs.cloud.google.com/docs/authentication/use-service-account-impersonation) for accessing your cloud resources.
106
+
* Assign the service account a role with [limited permissions](https://docs.cloud.google.com/iam/docs/roles-overview).
107
+
* Prevent unwanted cross-org agent access by utilizing **Principal Access Boundaries** to scope your agent to [projects](https://docs.cloud.google.com/iam/docs/principal-access-boundary-policies#use-case-one-project) you intend the agent to access.
108
+
109
+
> [!NOTE]
110
+
> The Principal Access Boundary condition should bind the policy to the service accounts you intend to restrict.
0 commit comments