stackql
Query, provision and operate Cloud, SaaS, API and Model Context Protocol (MCP) resources through a unified SQL-based framework for humans and AI agents.
No outside reports on file
StackQL gives AI agents direct power over your cloud infrastructure through SQL, so improper permission limits, weak credentials, or prompt injection could cause real damage to live resources.
Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsRequires API key or tokenREVIEW
- Package sourceGitHub (stackql/stackql)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/stackql/stackql ↗
About Stackql
StackQL lets you query and manage cloud resources (like AWS, Azure, Google Cloud) and APIs using SQL commands instead of learning each service's own language. It works as an MCP server, so AI agents can use it to understand and control cloud infrastructure through standard SQL queries.
Who it’s for
Cloud engineers, DevOps teams, and AI systems that need to inspect or provision cloud resources programmatically. It's designed for both humans writing SQL and AI agents working through MCP connections.
Alternatives
- Terraform with Claude/AI wrappers: Infrastructure-as-code tool with AI integration for planning changes
- AWS CloudFormation: Native AWS template language; less SQL-like but simpler permission model
- OpenTofu: Open-source Terraform alternative for multi-cloud infrastructure management
- Pulumi: Infrastructure as code using Python/Go/TypeScript instead of SQL
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README on https://github.com/stackql/stackql (opens external site) for installation and configuration steps specific to your environment.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 1.1k
- Listing last refreshed
- 2026-10-29
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-29).
Risks to watch for
- Cloud account access: The tool needs credentials (API keys, cloud tokens) to query and modify your cloud resources; compromised credentials could expose all connected accounts
- SQL injection via prompts: AI agents given malformed user input might construct SQL queries that do unintended operations on your infrastructure
- Overly broad permissions: If the tool runs with admin-level cloud credentials, a bug or misuse could affect all your resources, not just what's needed
- Data leakage in queries: Results from cloud queries may contain sensitive information (database contents, configuration secrets, user IDs) that could be logged or leaked
- Hidden destructive commands: SQL UPDATE or DELETE statements could silently modify or remove cloud resources if the AI agent is given insufficient constraints
How to lower the risk
Least-privilege permissions
- Use cloud IAM to restrict the tool's credentials to only the services and actions it actually needs
- Never use root or master account credentials; create a dedicated service account
Network isolation
- Run the MCP server on a private, controlled network if possible
- Restrict outbound API calls to only the cloud providers you use
Monitoring
- Log all SQL queries and cloud operations the tool performs
- Set up alerts for any DELETE, UPDATE, or resource deletion commands
- Review cloud audit logs regularly for unexpected changes
Red flags to watch for
- Unexpected queries to resources outside your normal infrastructure
- Rapid or bulk operations that suggest a loop or injection attack
- Credentials or configuration details appearing in query results or logs
Questions
How do I install Stackql?
Stackql does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/stackql/stackql.
Are there security reports about Stackql?
No reports found for this package in our research (last checked 2026-10-29). Stackql currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include cloud account access, sql injection via prompts, overly broad permissions.
Is Stackql actively maintained?
Stackql has 1.1k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/stackql/stackql before pinning it in production.
What are alternatives to Stackql?
Notable alternatives to Stackql include Terraform with Claude/AI wrappers (Infrastructure-as-code tool with AI integration for planning changes), AWS CloudFormation (Native AWS template language), OpenTofu (Open-source Terraform alternative for multi-cloud infrastructure management), Pulumi (Infrastructure as code using Python/Go/TypeScript instead of SQL). You can also compare Stackql side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Stackql? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/stackql-stackql)HTML embed:
<a href="https://agentarmorhq.com/skills/stackql-stackql"><img src="https://agentarmorhq.com/api/badge/stackql-stackql" alt="AgentArmorHQ Risk Grade for Stackql" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "stackql-stackql"Share with your security lead
Need sign-off to use stackql? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: stackql
- **Listing URL:** https://agentarmorhq.com/skills/stackql-stackql
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.1k GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** Requires API key or token
- **Package source:** GitHub (stackql/stackql)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/stackql/stackql
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- stackql
- Source code
- github.com/stackql/stackql
- Est. context load
- ~1.2k tokens / turn (~7 tool schemas, 0.6% of 200k context)
- Popularity
- 1.1k GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-23
Community
Discussions for Stackql
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude