PgBeam Docs

mcp

Start the MCP server for AI agent integration.

Start a Model Context Protocol (MCP) server that exposes every API endpoint as a tool over JSON-RPC 2.0 via stdio.

Usage

pgbeam mcp

Configuration

Add the MCP server to your AI tool's configuration:

.claude/mcp.json
{
  "mcpServers": {
    "pgbeam": {
      "command": "pgbeam",
      "args": ["mcp"],
      "env": {
        "PGBEAM_TOKEN": "pbk_..."
      }
    }
  }
}
.cursor/mcp.json
{
  "mcpServers": {
    "pgbeam": {
      "command": "pgbeam",
      "args": ["mcp"],
      "env": {
        "PGBEAM_TOKEN": "pbk_..."
      }
    }
  }
}
{
  "mcpServers": {
    "pgbeam": {
      "command": "pgbeam",
      "args": ["mcp"],
      "env": {
        "PGBEAM_TOKEN": "pbk_..."
      }
    }
  }
}

On this page