Simple Snowflake MCP

Instructions

Implementation Reference

• src/simple_snowflake_mcp/server.py:765-782 (handler)

  The execution handler for the 'list-databases' tool. Constructs and executes a SHOW DATABASES SQL query with optional pattern filter, handles output formatting based on 'include_details' parameter, and returns results as text content.

  elif name == "list-databases":
      pattern = args.get("pattern")
      include_details = args.get("include_details", False)
      
      query = "SHOW DATABASES"
      if pattern:
          query += f" LIKE '{pattern}'"
      
      result = _safe_snowflake_execute(query, "List databases")
      if result["success"]:
          if include_details:
              output = json.dumps(result["data"], indent=2, default=str)
          else:
              databases = [row.get("name", "") for row in result["data"]]
              output = "\n".join(databases)
          return [types.TextContent(type="text", text=output)]
      else:
          return [types.TextContent(type="text", text=f"Snowflake error: {result['error']}")]

• src/simple_snowflake_mcp/server.py:623-642 (registration)

  Registers the 'list-databases' tool in the list_tools() handler, defining its description and input schema for validation of 'pattern' (string with wildcards) and 'include_details' (boolean) parameters.

  types.Tool(
      name="list-databases",
      description="List all accessible Snowflake databases with optional filtering",
      inputSchema={
          "type": "object",
          "properties": {
              "pattern": {
                  "type": "string",
                  "description": "Filter databases by name pattern (supports wildcards)",
                  "examples": ["PROD_%", "%_DEV"]
              },
              "include_details": {
                  "type": "boolean", 
                  "default": False,
                  "description": "Include database details and metadata"
              }
          },
          "additionalProperties": False
      },
  ),

• src/simple_snowflake_mcp/server.py:626-641 (schema)

  JSON schema definition for the 'list-databases' tool inputs, specifying properties for filtering and details inclusion.

  inputSchema={
      "type": "object",
      "properties": {
          "pattern": {
              "type": "string",
              "description": "Filter databases by name pattern (supports wildcards)",
              "examples": ["PROD_%", "%_DEV"]
          },
          "include_details": {
              "type": "boolean", 
              "default": False,
              "description": "Include database details and metadata"
          }
      },
      "additionalProperties": False
  },

• src/simple_snowflake_mcp/server.py:168-194 (helper)

  Helper function that performs safe Snowflake query execution with connection management, result parsing, and error handling, directly called by the list-databases handler.

  def _safe_snowflake_execute(query: str, description: str = "Query") -> Dict[str, Any]:
      """
      Safely execute a Snowflake query with proper error handling and logging.
      """
      try:
          logger.info(f"Executing {description}: {query[:100]}...")
          ctx = snowflake.connector.connect(**SNOWFLAKE_CONFIG)
          cur = ctx.cursor()
          cur.execute(query)
          
          # Handle different query types
          if cur.description:
              rows = cur.fetchall()
              columns = [desc[0] for desc in cur.description]
              result = [dict(zip(columns, row)) for row in rows]
          else:
              result = {"status": "success", "rowcount": cur.rowcount}
              
          cur.close()
          ctx.close()
          logger.info(f"{description} completed successfully")
          return {"success": True, "data": result}
          
      except Exception as e:
          logger.error(f"{description} failed: {str(e)}")
          return {"success": False, "error": str(e), "data": None}