mcp-sql-metrics

JuanPinilla198/mcp-sql-metrics
★ 0 stars Python Database Updated 5d ago
MCP server that exposes read-only SQL queries as typed tools
View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-sql-metrics": {
      "command": "uvx",
      "args": [
        "mcp-sql-metrics"
      ]
    }
  }
}

Or install with pip: pip install mcp-sql-metrics

README Excerpt

An [MCP](https://modelcontextprotocol.io) server that exposes read-only SQL queries as typed tools. You declare your queries in a YAML file. The server turns each one into an MCP tool with a real argument schema, runs it as a parameterized read against PostgreSQL, and returns the rows as JSON. The intuitive way to let a language model answer questions about your data is to export the data and put it in the prompt. That approach breaks down for three reasons:

Tools (7)

DATABASE_URLQUERIES_FILEdescriptionmax_rowsparamssqltimeout_ms

Topics

agentsllmmcpmodel-context-protocolpostgresqlpython
📊
Working with market or time-series data?
The Polymarket Historical Dataset — 18.5M+ price snapshots across 18,600+ prediction markets (CSV + SQLite). Built for backtesting & ML.
View dataset →