Stackql

Created By
stackql10 hours ago
Open source SQL-native query and provisioning engine for cloud and SaaS infrastructure. Ships as a single signed binary with MCP tools for provider discovery, schema exploration, queries, and lifecycle operations.
Overview

StackQL MCP Server

StackQL is an open-source, SQL-native query and provisioning engine for cloud and SaaS infrastructure. The MCP server exposes StackQL's provider registry and query engine as MCP tools, letting agents discover providers, explore schemas, and run live SQL queries against AWS, Azure, Google, GitHub, Databricks, Okta, and other providers - all through a single signed binary with no runtime dependencies.

Tools

  • list_providers, pull_provider, list_registry - discover and install providers from the StackQL registry
  • list_services, list_resources, describe_resource, list_methods, describe_method - explore provider schemas
  • run_select_query, validate_select_query - live SQL queries against cloud APIs
  • run_mutation_query, run_lifecycle_operation - provisioning and lifecycle operations (gated by server mode)
  • server_info - server and registry status

Install (Claude Desktop - one-click)

Download the prebuilt MCP Bundle for your platform from the latest release - stackql-mcp-<platform>.mcpb - then Settings -> Extensions -> Install Extension. No separate StackQL install needed. Each bundle has a .sha256 alongside it.

Install (manual, any stdio MCP client)

With the stackql binary installed, use the server config shown above. Replace /Users/yourname with your home directory. The --approot and audit settings matter: some MCP clients launch servers with an unwritable working directory.

Authentication

Provider credentials are passed via StackQL's standard --auth flag or environment variables - see the provider docs. The github provider works without credentials for public data.

Server Config

{
  "mcpServers": {
    "stackql": {
      "command": "stackql",
      "args": [
        "mcp",
        "--mcp.server.type=stdio",
        "--approot",
        "/Users/yourname/.stackql",
        "--mcp.config",
        "{\"server\": {\"audit\": {\"disabled\": true}}}"
      ]
    }
  }
}
Project Info
Created At
10 hours ago
Updated At
10 hours ago
Author Name
stackql
Star
-
Language
-
License
-
Category

Recommend Servers

View All
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

11 hours ago
Tavily Mcp
@tavily-ai

JavaScript
a year ago
Puter Mcp

2 days ago
Linkpulse

14 hours ago