M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
S

StackQL MCP Server

Official
Query and provision cloud infrastructure with SQL.
How to install ↓ Compare GitHub source repository ↗
Category
Other
Stars
★ 1.1k Very popular
Transport
stdio (local process)
Runtime
Node.js · Python · Docker · Prebuilt binary
Credentials
Optional API key
License
MIT
Last commit
55FMRS · C

The source identifies this as a StackQL-maintained server using stdio transport, distributed through npm, PyPI, Docker, GitHub Actions, and .mcpb bundles. It is suited to SQL-based querying and provisioning of cloud and SaaS resources; named tools, exact authentication scopes, and complete client compatibility are not specified in the source.

Strongest · Setup experience 13/20 Weakest · Security and permissions 8/20

Reliability
9/20
Security and permissions
8/20
Maintenance
13/20
Documentation
12/20
Setup experience
13/20
Why each score
Reliability 9/20
The manifest specifies stdio transport, multi-platform packages, versions, and hashes, while the README provides startup commands, making a basic handshake path plausible. Points are deducted because the supplied material contains no committed tests for MCP key paths, CI execution evidence, tool list, or error-handling evidence, so declared tools and behavior cannot be verified; static calibration limits this score to 12 or below.
Security and permissions 8/20
The material shows that the server can access and provision cloud and SaaS resources, involving external networks, credentials, and potentially consequential infrastructure side effects. The README explicitly identifies read_only as the GitHub Actions default, but does not establish least privilege for general MCP use, tool-level scoping, confirmation for dangerous operations, credential boundaries, or data-flow controls. No red-line risk is evidenced, so this is not a red-line score, but the lack of security-control evidence warrants substantial deductions.
Maintenance 13/20
The repository is not archived and provides an MIT license, clear repository ownership, a current version, and multiple distribution channels, indicating an identifiable maintenance and update path. Points are deducted because the supplied material does not show commit cadence, maintainer response history, dependency-update policy, vulnerability disclosure, or a security-response channel; the open-issue count is not evidence of maintenance quality.
Documentation 12/20
The README covers project purpose, MCP startup, npm/PyPI/Docker/.mcpb/GitHub Actions installation, client configuration, an authentication placeholder, query examples, and read-only mode. Points are deducted because it lacks a concrete tool catalog and parameter specifications, permission model, limits, cost implications, compatibility details, and troubleshooting evidence, with important guidance delegated to external documentation links.
Setup experience 13/20
The project offers npm, PyPI, Docker, .mcpb, and GitHub Actions installation paths, plus mainstream MCP client configuration examples and stated Windows, macOS, and Linux support. Points are deducted because authentication prerequisites, runtime requirements, version compatibility, and connection verification are incomplete; some paths depend on external tools or manual downloads, and the static material contains no verifiable execution evidence, so the score remains at or below 15.

Static review · not runListed 2026-07-29

Read the FMRS scoring method →

Fit and risk

What it can accessUses the networkChanges third-party account data

Best for

  • Teams needing a unified SQL interface across cloud and SaaS providers
  • Users who want AI agents to access cloud resources in a structured way
  • Cloud operations, security, FinOps, and infrastructure-as-code workflows

Not for

  • Users who only need local file or browser automation
  • Environments that cannot grant cloud or SaaS API access
  • Users expecting a tool inventory with individually named MCP tools, which the source does not provide

Required permissions

  • Provider authentication must be supplied through --auth or the client configuration
  • Effective permissions depend on the provider credentials and requested operations; the server supports querying and provisioning
  • GitHub Actions defaults to read_only mode, which is intended as the safe CI default

Risks and side effects

  • Provisioning or modifying resources can cause real infrastructure changes
  • Overprivileged credentials can broaden the impact across cloud or SaaS resources
  • AI-generated SQL or API operations should be reviewed before execution
  • Cross-cloud operations may create cost, compliance, and security consequences

Setup

Before you start

Runtime：Node.js · Python · Docker · Prebuilt binary

Configure an MCP-capable client with command set to npx and args set to -y and @stackql/mcp-server. Alternative distribution methods include PyPI, Docker, GitHub Actions, and platform-specific .mcpb bundles. Refer to StackQL documentation for client configuration, authentication, and server modes.

.cursor/mcp.json 
{"mcpServers":{"stackql":{"command":"npx","args":["-y","@stackql/mcp-server"]}}}

Shown for Cursor. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json
{
  "servers": {
    "stackql": {
      "command": "npx",
      "args": [
        "-y",
        "@stackql/mcp-server"
      ]
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal
claude mcp add stackql -- npx -y @stackql/mcp-server

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

Add the stackql server to your MCP client config (e.g. npx -y @stackql/mcp-server), restart the client, confirm the stackql server connects, and run a simple SQL query (e.g. listing resources from a provider) to prove the connection works.

Troubleshooting

  1. Verify that the client supports MCP over stdio
  2. Confirm that npx, the PyPI package, Docker, or the relevant platform bundle is available
  3. Check authentication parameters and provider credential permissions
  4. Validate connectivity with read-only or query operations before provisioning
  5. Consult StackQL documentation for client configuration, authentication, and server modes

Things to try

Once connected, you can ask your AI assistant things like:

  • List all AWS EC2 instances in us-east-1 with their status
  • Count and describe running VMs across all my cloud accounts
  • Query GitHub repo star counts and contributors using SQL
  • Use StackQL to list Azure storage accounts in my subscription

Use cases

Query cloud and SaaS resources with SQL
Manage cross-cloud assets and perform security audits
Let AI agents query or provision infrastructure through MCP
Automate infrastructure provisioning and compliance checks with GitHub Actions

Supported clients

ClaudePartial support
VS CodePartial support
CursorPartial support

Listed from the project's documentation, not tested by this site.

Overview

StackQL MCP Server is StackQL’s SQL-native engine for querying and provisioning cloud infrastructure over MCP. It serves more than 40 cloud and SaaS providers by transpiling SQL statements into provider API requests for querying, creating, modifying, and operating resources.

Similar servers

Telegram MCP Server 70 · B

Telegram MCP server powered by Telethon to let MCP clients read chats, manage groups, and send/modify messages, media, contacts, and settings.

★ 1.8k · Tools 76 Compare with this →
Compare with other MCP servers

Source revision 76a37e6b3b4a Data synced 2026-10-19 Read the FMRS scoring method