Stackql
Query, provision and operate Cloud and SaaS resources and APIs using an extensible SQL based framework
What is Stackql?
Stackql is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to query, provision and operate cloud and saas resources and apis using an extensible sql based framework
Query, provision and operate Cloud and SaaS resources and APIs using an extensible SQL based framework
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Query, provision and operate Cloud and SaaS resources and AP
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx stackqlConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Stackql
StackQL is an open-source SQL framework that lets AI agents query, provision, and operate cloud and SaaS resources across AWS, GCP, Azure, GitHub, Okta, and dozens more providers using familiar SQL syntax. The engine translates SQL statements into the appropriate cloud provider API calls, so agents can write 'SELECT id, status FROM aws.ec2.instances WHERE region = us-east-1' without learning each provider's REST API. This makes StackQL a powerful tool for cloud security posture management (CSPM), infrastructure auditing, and DevSecOps automation driven by natural language.
Prerequisites
- StackQL binary installed (Homebrew, Chocolatey, or direct download)
- Cloud provider credentials configured for the providers you want to query (e.g. AWS credentials via environment variables or ~/.aws/credentials)
- An MCP-compatible client such as Claude Desktop or Cursor (if using StackQL as an MCP server)
- Docker (optional, for running StackQL in a container)
Install StackQL
Install StackQL using your operating system's package manager, or download the binary directly.
# macOS
brew install stackql
# Windows (Chocolatey)
choco install stackql
# Linux
curl -L https://bit.ly/stackql-zip -O && unzip stackql-zip
# Docker
docker pull stackql/stackqlConfigure cloud provider authentication
Set up credentials for the cloud providers you want to query. StackQL accepts provider-specific auth configuration via the --auth flag as a JSON string.
# AWS example: set standard AWS env vars
export AWS_ACCESS_KEY_ID="AKIA..."
export AWS_SECRET_ACCESS_KEY="..."
export AWS_DEFAULT_REGION="us-east-1"
# Then pass to stackql
export AUTH='{"aws": {"type": "env", "credentialsenvvar": "AWS_SECRET_ACCESS_KEY", "keyIDenvvar": "AWS_ACCESS_KEY_ID"}}' Test with an interactive shell query
Launch the interactive StackQL shell and run a test query against your cloud provider to confirm authentication is working.
stackql shell --auth="${AUTH}"
-- Inside the shell:
SELECT id, instance_type, state FROM aws.ec2.instances WHERE region = 'us-east-1';Configure StackQL as an MCP server
Add StackQL to your MCP client configuration. StackQL can be invoked as a command-line process that accepts SQL queries from the MCP protocol.
{
"mcpServers": {
"stackql": {
"command": "stackql",
"args": ["srv", "--auth", "${AUTH}"],
"env": {
"AWS_ACCESS_KEY_ID": "AKIA...",
"AWS_SECRET_ACCESS_KEY": "...",
"AWS_DEFAULT_REGION": "us-east-1"
}
}
}
}Restart your MCP client and run a cloud query
Restart the client and ask the AI to query your cloud resources. StackQL will translate the SQL to API calls and return structured results.
Stackql Examples
Client configuration
Claude Desktop config launching StackQL in server mode with AWS credentials from environment variables.
{
"mcpServers": {
"stackql": {
"command": "stackql",
"args": ["srv"],
"env": {
"AWS_ACCESS_KEY_ID": "AKIA...",
"AWS_SECRET_ACCESS_KEY": "...",
"AWS_DEFAULT_REGION": "us-east-1"
}
}
}
}Prompts to try
Use these prompts once StackQL is connected to your MCP client.
- "List all running EC2 instances in us-east-1 and show their instance type and state."
- "Find all S3 buckets that do not have server-side encryption enabled."
- "Show me all IAM users who have not logged in for more than 90 days."
- "List all open GitHub issues in the stackql/stackql repository."
- "Query all GCP compute instances across all zones and export to a table."Troubleshooting Stackql
stackql command not found after installation
On macOS, run 'brew link stackql' or ensure /usr/local/bin is in your PATH. On Linux, move the extracted binary to /usr/local/bin: 'sudo mv stackql /usr/local/bin/'.
Authentication errors when querying AWS resources
Verify your AWS credentials are valid with 'aws sts get-caller-identity'. Ensure the --auth JSON structure matches the StackQL provider spec for AWS. Consult the StackQL docs at https://stackql.io/docs for the exact auth schema per provider.
SQL query returns no rows when resources clearly exist
Check the region filter in your WHERE clause — StackQL requires explicit region scoping for most AWS resources. Run 'SHOW SERVICES IN aws;' inside the shell to confirm the provider is loaded correctly.
Frequently Asked Questions about Stackql
What is Stackql?
Stackql is a Model Context Protocol (MCP) server that query, provision and operate cloud and saas resources and apis using an extensible sql based framework It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Stackql?
Follow the installation instructions on the Stackql GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Stackql?
Stackql works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Stackql free to use?
Yes, Stackql is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Stackql Alternatives — Similar Cloud Services Servers
Looking for alternatives to Stackql? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Stackql in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Stackql?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.