---
title: "db-context-engineering"
description: "Context Engineering Agent for generating natural language to SQL templates, facets, and value searches."
canonical: https://agentpluginsdirectory.com/plugins/db-context-engineering
last-updated: 2026-09-21
---

# db-context-engineering
Context Engineering Agent for generating natural language to SQL templates, facets, and value searches.
- Slug: db-context-engineering
- Publisher: Google Cloud Platform
- Repository: https://github.com/GoogleCloudPlatform/db-context-enrichment
- Manifest: plugin/plugin.json
- Version: 0.7.3
- License: Apache-2.0
- Category (editorial): databases
- Skills: 7 (context-engineering-bootstrap, context-engineering-dataset-generation, context-engineering-evaluate, context-engineering-hillclimb, context-engineering-init, context-engineering-workflow, context-generation-guide)
- MCP servers: 2 (db-context-engineering, toolbox)
- Stars: 39
- Repository created: 2025-02-10
- Repository last pushed: 2026-09-18
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/db-context-engineering
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What db-context-engineering does, in the publisher's words

The Context Engineering Agent is an AI coding agent plugin designed to run in developer agent harnesses (such as Claude Code, Antigravity, or Gemini CLI). It generates, evaluates, and iteratively tunes tailored context artifacts (ContextSets comprising Templates, Facets, and Value Searches) to enrich database schemas for Gemini Data Analytics's data agent developer platform tools, supporting both relational SQL and Graph Query Language (GQL) across AlloyDB, Cloud SQL (PostgreSQL / MySQL), and Cloud Spanner (GoogleSQL & Spanner Graph).

When building data agents and natural language analytics interfaces, accurately translating user intent into database queries, whether relational SQL, pure GQL, or hybrid graph queries, is critical.

As outlined in Build Context with Context Engineering Agent (AlloyDB | Cloud SQL: PostgreSQL / MySQL | Spanner (GoogleSQL)), by optimizing a ContextSet to match your application's expected query stream, the QueryData API acts as a data agent tool capable of achieving ~100% NL-to-SQL/GQL translation accuracy with low latency.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/GoogleCloudPlatform/db-context-enrichment/HEAD/README.md

## Skills

- context-engineering-bootstrap: Guides the agent to bootstrap an initial ContextSet (templates, facets, and value searches) by deducing key information from the database schema and generating a ContextSet file.
- context-engineering-dataset-generation: Generate or expand a golden evaluation dataset of SQL/Question (NLQ+SQL) pairs for evaluating NL-to-SQL translation accuracy on a target database.
- context-engineering-evaluate: Guides the agent to execute an evaluation of a ContextSet against a golden NLQ+SQL dataset using the Evalbench framework.
- context-engineering-hillclimb: Guides the agent to perform hill-climbing iterations to improve a ContextSet based on Evalbench evaluation results.
- context-engineering-init: Orchestrates the initialization workflow for context engineering, and provides helper workflow for setting up database connections by creating or updating tools.yaml configurations.
- context-engineering-workflow: Context engineering for Gemini Data Analytics API's data agent developer platform tools. Generates, evaluates, and iteratively optimizes a ContextSet (Templates, Facets, Value Searches) to maximize Natural-Language-to-SQL translation accuracy. Use this skill to run the automated setup, NL-SQL pair…
- context-generation-guide: Guidelines and best practices for generating context items (Templates, Facets, Value Searches). Use this skill whenever the user asks to create, author, or generate context for database enrichment, or asks for examples and instructions on how to write templates, facets, or value searches. It helps…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- db-context-engineering: transport: stdio; command: uvx google-cloud-db-context-engineering@0.7.2
- toolbox: transport: stdio; command: uvx toolbox-server@1.4.0 --config autoctx/tools.yaml --stdio

Read from the plugin's own mcp.json. Environment variable names only, never values.