StackQL MCP Server MCP Server
io.github.stackql/stackql-mcp
Query and provision cloud infrastructure across 40+ providers using SQL via MCP
What is the StackQL MCP Server MCP server?
The StackQL MCP Server is a SQL-native query and provisioning engine for cloud infrastructure that integrates with AI agents like Claude and Cursor. It allows you to query and manage resources across 40+ cloud and SaaS providers (AWS, Google Cloud, Azure, GitHub, Okta, etc.) using standard SQL semantics, transpiling SQL statements into API requests.
StackQL MCP exposes cloud and SaaS APIs as queryable SQL tables, letting you write SELECT, INSERT, UPDATE, and DELETE statements against infrastructure resources. Use it to audit cloud state, provision resources, enforce compliance, or gather FinOps data across multiple cloud providers without learning provider-specific APIs or SDKs.
How to install StackQL MCP Server
Copy-paste configuration for popular MCP clients.
Tools & capabilities
Tools this server exposes to the agent.
SQL query execution— Execute SELECT, INSERT, UPDATE, and DELETE statements against cloud provider APIsMulti-provider resource querying— Query resources across 40+ cloud and SaaS providers including AWS, Google Cloud, Azure, GitHub, Okta, and othersInfrastructure provisioning— Create, modify, and delete cloud resources using SQL statementsOutput formatting— Return results in JSON, CSV, table, or text formatsVariable and parameter support— Pass parameters to queries using jsonnet or JSON
Use cases
- Query EC2 instances, S3 buckets, and other AWS resources across regions using SQL
- Audit cloud security and compliance by querying IAM policies, network configurations, and resource tags across multiple cloud providers
- Provision infrastructure resources (VMs, databases, networks) by writing INSERT statements instead of using provider CLIs
- Generate FinOps reports by querying billing and resource utilization data across AWS, Google Cloud, and Azure
- Automate cloud resource management in CI/CD pipelines via GitHub Actions or other agentic workflows
StackQL MCP Server MCP server FAQ
StackQL MCP is a SQL-native interface to 40+ cloud and SaaS providers. It transpiles SQL queries into API calls, letting you query and provision infrastructure using standard SQL instead of provider-specific tools.
Yes, StackQL is open-source under the MIT License and free to use.
Add a configuration block to your MCP client config pointing to one of the install vectors: npm (@stackql/mcp-server), PyPI (stackql-mcp-server), Docker (stackql/stackql-mcp), or download a .mcpb bundle for your platform.
StackQL requires credentials for the cloud providers you want to query (AWS, Google Cloud, Azure, etc.). Pass credentials via the --auth flag or environment variables. GitHub Actions mode defaults to read-only for safety.
Yes, StackQL supports a read-only mode suitable for audits and CI/CD workflows, preventing accidental infrastructure changes.
StackQL can return results as JSON, CSV, table, or text format via the --output flag.
README (reference)
Source of truth, from the repository.
Deploy, manage and query cloud resources and interact with APIs using SQL
The Universal Interface for the Agentic Era. Configuration-as-Data. Infrastructure-as-Context.
<!-- <h3 align="center">SQL based XOps, observability and middleware framework</h3> --> <p align="center">Read the docs »
Raise an Issue ·
Request a Feature ·
Developer Guide ·
BYO Providers
About The Project
StackQL is an open-source project built with Golang that allows you to create, modify and query the state of services and resources across different local and remote interfaces, using SQL semantics. Such interfaces canonically include, but are not limited to, cloud and SaaS providers (Google, AWS, Azure, Okta, GitHub, etc.). <br /> <br />

How it works
StackQL is a standalone application that can be used in client mode (via exec or shell) or accessed via a Postgres wire protocol client (psycopg2, etc.) using server mode (srv).
StackQL parses SQL statements and transpiles them into API requests to the (cloud) resource provider. The API calls are then executed and the results are returned to the user.
StackQL provider interfaces are canonically defined in OpenAPI extensions to the providers' specification. These definitions are then used to generate the SQL schema and the API client. The source for the provider definitions are stored in the StackQL Registry. The semantics of provider interactions are defined in our any-sdk library. For more detail on nuts and bolts, please see the local AGENTS.md file and that of any-sdk.
flowchart LR
subgraph StackQL
direction BT
subgraph ProviderDefs
Registry[Provider Registry Docs]
end
subgraph App
Proc[$ stackql exec\n$ stackql shell\n$ stackql srv]
style Proc fill:#000,stroke:#000,color:#fff,text-align:left;
%% ,font-family:'Courier New', Courier, monospace
end
end
User((User)) <--> StackQL <--> Provider[Cloud Provider API]
ProviderDefs --> App
More detailed design documentation can be found in the here.
</details>MCP Server
StackQL is an MCP server - SQL over 40+ cloud and SaaS providers for AI agents. Point any MCP-capable client (Claude, VS Code, Cursor, etc.) at StackQL and it can query and provision cloud resources using SQL.
Run it over stdio:
stackql mcp --mcp.server.type=stdio
StackQL MCP is published to the Official MCP Registry as io.github.stackql/stackql-mcp and distributed via npm, PyPI, Docker, a GitHub Action and .mcpb bundles. Pick an install vector and add the matching block to your MCP client config:
{
"mcpServers": {
"stackql": {
"command": "npx",
"args": ["-y", "@stackql/mcp-server"]
}
}
}
</details>
<details>
<summary><b>PyPI (uvx)</b></summary>
{
"mcpServers": {
"stackql": {
"command": "uvx",
"args": ["stackql-mcp-server"]
}
}
}
</details>
<details>
<summary><b>Docker</b></summary>
{
"mcpServers": {
"stackql": {
"command": "docker",
"args": ["run", "-i", "--rm", "stackql/stackql-mcp"]
}
}
}
</details>
<details>
<summary><b>.mcpb bundle</b></summary>
Download the bundle for your platform from the latest release and install it in your MCP client (one-click in clients that support
.mcpb).
stackql-mcp-linux-x64.mcpbstackql-mcp-linux-arm64.mcpbstackql-mcp-windows-x64.mcpbstackql-mcp-darwin-universal.mcpb
Wire StackQL MCP into agentic CI workflows. Defaults to
read_onlymode, the safe default for CI.
- uses: stackql/setup-stackql-mcp@v1
with:
mode: read_only
</details>
For client-specific setup, authentication and server modes, see the full MCP install and usage docs.
Installation
StackQL is available for Windows, MacOS, Linux, Docker, GitHub Actions and more. See the installation instructions below for your platform.
<details> <summary><b>Installing on MacOS</b></summary>- Homebrew (
amd64andarm64)brew install stackqlorbrew tap stackql/tap && brew install stackql/tap/stackql
- MacOS PKG Installer (
amd64andarm64)- download the latest MacOS PKG installer for StackQL
- run the installer and follow the prompts
- MSI Installer
- download the latest MSI installer for StackQL
- run the installer and follow the prompts
- Chocolatey
- install Chocolatey
- run
choco install stackql
- ZIP Archive
- download the latest Windows ZIP archive for StackQL
- extract the archive (code signed
stackql.exefile) to a directory of your choice - add the directory to your
PATHenvironment variable (optional)
- ZIP Archive
- download the latest Linux ZIP archive for StackQL
- or via
curl -L https://bit.ly/stackql-zip -O && unzip stackql-zip
- or via
- extract the archive (
stackqlfile) to a directory of your choice - add the directory to your
PATHenvironment variable (optional)
- download the latest Linux ZIP archive for StackQL
View all available StackQL images on DockerHub. Images available include
stackql,stackql-jupyter-demoand more. Pull the latest StackQL base image using:
docker pull stackql/stackql
</details> <details> <summary><b>Using StackQL with GitHub Actions</b></summary>Want findings, not infrastructure? Run a read-only cross-cloud security & FinOps audit with the standard image in one command — see the Docker audit quickstart.
</details>Use StackQL in your GitHub Actions workflows to automate cloud infrastructure provisioning, IaC assurance, or compliance/security. Available GitHub Actions include:
setup-stackql,stackql-execand more
Usage
StackQL can be used via the interactive REPL shell, or via the exec command or ran as a server using the Postgres wire protocol.
ℹ️ StackQL does not require or install a database.
-
Interactive Shell
# run interactive stackql queries stackql shell --auth="${AUTH}" -
Execute a statement or file
stackql exec --auth="${AUTH}" -i myscript.iql --iqldata vars.jsonnet --output json # or stackql exec --auth="${AUTH}" "SELECT id, status FROM aws.ec2.instances WHERE region = 'us-east-1'"ℹ️ output options of
json,csv,tableandtextare available for theexeccommand using the--outputflagℹ️ StackQL supports passing parameters using
jsonnetorjson, see Using Variables -
Server
# serve client requests over the Postgres wire protocol (psycopg2, etc.) stackql srv --auth="${AUTH}"
For more examples, please check our Blog
<!-- ## Roadmap See our [__roadmap__](https://github.com/othneildrew/Best-README-Template/issues) to see where we are going with the project. -->Contributing
Contributions are welcome and encouraged. For more information on how to contribute, please see our contributing guide.
License
Distributed under the MIT License. See LICENSE for more information. Licenses for third party software we are using are included in the /docs/licenses directory.
Contact
Get in touch with us via Twitter at @stackql, email us at info@stackql.io or start a conversation using discussions.
Acknowledgements
Forks of the following support our work:
- vitess
- kin-openapi
- gorilla/mux
- readline
- psql-wire
- mcp-postgres
- the
golangMCP SDK - ...and more. Please excuse us for any omissions.
We gratefully acknowledge these pieces of work.
Related MCP servers

Phonebook
Self-hosted gallery of SwiftUI #Preview and Jetpack Compose @Preview screens, no SaaS required.

AI-optimized patent data marketplace providing structured JSON datasets.

SEC EDGAR Filings MCP
SEC EDGAR MCP: search, preview, purchase filings. x402 USDC on Polygon. xpay + Cloud Run upstream.
MCP server for Directus 12 — items, collections, files, flows, users, and schema tools
Dart AI task management MCP with batch operations, DartQL selectors, CSV import, zero context rot

DevTool MCP
AI coding agent with browser superpowers: screenshots, DOM inspection, error capture, and real-time debugging.

