Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/gemini-cli-extensions/cloud-sql-sqlserverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/gemini-cli-extensions/cloud-sql-sqlserver/gemini-extension)<a href="https://agentmods.dev/plugins/gemini-cli-extensions/cloud-sql-sqlserver/gemini-extension"><img src="https://agentmods.dev/badge/plugins/gemini-cli-extensions/cloud-sql-sqlserver/gemini-extension/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/gemini-cli-extensions/cloud-sql-sqlserver/gemini-extension"><img src="https://agentmods.dev/badge/plugins/gemini-cli-extensions/cloud-sql-sqlserver/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cloud-sql-sqlserver scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "cloud-sql-sqlserver",
"version": "0.2.0",
"description": "Connect to Cloud SQL for SQL Server",
"mcpServers": {
"cloud-sql-mssql": {
"command": "npx",
"args": [
"-y",
"@toolbox-sdk/[email protected]",
"--prebuilt",
"cloud-sql-mssql",
"--stdio"
]
}
},
"contextFileName": "CLOUD-SQL-SQLSERVER.md",
"settings": [
{
"name": "Project Name",
"description": "Name of the Google Cloud project",
"envVar": "CLOUD_SQL_MSSQL_PROJECT"
},
{
"name": "Region",
"description": "Region of the Cloud SQL instance",
"envVar": "CLOUD_SQL_MSSQL_REGION"
},
{
"name": "Instance ID",
"description": "ID of the Cloud SQL instance",
"envVar": "CLOUD_SQL_MSSQL_INSTANCE"
},
{
"name": "Database",
"description": "Name of the database",
"envVar": "CLOUD_SQL_MSSQL_DATABASE"
},
{
"name": "User",
"description": "Username of the database user",
"envVar": "CLOUD_SQL_MSSQL_USER"
},
{
"name": "Password",
"description": "Password of the database user",
"envVar": "CLOUD_SQL_MSSQL_PASSWORD"
},
{
"name": "Instance IP assignment",
"description": "(Optional) Type of the IP address: PUBLIC, PRIVATE, or PSC (Default: Public)",
"envVar": "CLOUD_SQL_MSSQL_IP_TYPE"
}
]
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 56 lines scan A 0c18875cb37a
cloud-sql-sqlserver is a plugin published in the GitHub repository gemini-cli-extensions/cloud-sql-sqlserver (9 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-22.
Other plugins, from other repositories
cloud-sql-postgresql
Create, connect, and interact with a Cloud SQL for PostgreSQL database and data.
cloud-sql-postgresql
Create, connect, and interact with a Cloud SQL for PostgreSQL database and data.
firestore-native
Connect and interact with Firestore databases, collections, and documents.
firestore-native
Connect and interact with Firestore databases, collections, and documents.
spanner
Connect and interact with Spanner data using natural language.
spanner
Connect and interact with Spanner data using natural language.