feat: browser_mcp — servidor MCP de control de navegador CDP (33 tools + pool de conexiones)

2026-06-06 10:57:13 +02:00
commit 6ecaf9a969
15 changed files with 1668 additions and 0 deletions
@@ -0,0 +1,110 @@
+package main
+
+import (
+	"context"
+
+	"github.com/mark3labs/mcp-go/mcp"
+	"github.com/mark3labs/mcp-go/server"
+
+	"fn-registry/functions/browser"
+)
+
+// registerInputTools wires press_key, scroll, handle_dialog. All MUTA.
+func registerInputTools(s *server.MCPServer, d *deps) {
+	if d.readOnly {
+		return
+	}
+	s.AddTool(pressKeyTool(), mcp.NewTypedToolHandler(d.handlePressKey))
+	s.AddTool(scrollTool(), mcp.NewTypedToolHandler(d.handleScroll))
+	s.AddTool(handleDialogTool(), mcp.NewTypedToolHandler(d.handleHandleDialog))
+}
+
+// ---- press_key (MUTA) ----
+
+type pressKeyArgs struct {
+	Port int    `json:"port"`
+	Key  string `json:"key"`
+}
+
+func pressKeyTool() mcp.Tool {
+	return mcp.NewTool("press_key",
+		mcp.WithDescription("Press a named key (Enter, Tab, Escape, ArrowDown, Backspace, ...) on the focused element."),
+		mcp.WithNumber("port", mcp.Description("CDP port. Default 9222.")),
+		mcp.WithString("key", mcp.Required(), mcp.Description("Key name, e.g. Enter, Tab, Escape, ArrowDown.")),
+	)
+}
+
+func (d *deps) handlePressKey(_ context.Context, _ mcp.CallToolRequest, a pressKeyArgs) (*mcp.CallToolResult, error) {
+	if a.Key == "" {
+		return mcp.NewToolResultError("key is required"), nil
+	}
+	err := d.withConn(portOr(a.Port), func(c *browser.CDPConn) error {
+		return browser.CdpPressKey(c, a.Key)
+	})
+	if err != nil {
+		return mcp.NewToolResultError(err.Error()), nil
+	}
+	return mcp.NewToolResultText("pressed " + a.Key), nil
+}
+
+// ---- scroll (MUTA) ----
+
+type scrollArgs struct {
+	Port   int     `json:"port"`
+	DeltaX float64 `json:"delta_x"`
+	DeltaY float64 `json:"delta_y"`
+}
+
+func scrollTool() mcp.Tool {
+	return mcp.NewTool("scroll",
+		mcp.WithDescription("Scroll the page by (delta_x, delta_y) pixels via a synthetic mouse wheel event."),
+		mcp.WithNumber("port", mcp.Description("CDP port. Default 9222.")),
+		mcp.WithNumber("delta_x", mcp.Description("Horizontal scroll delta in pixels. Default 0.")),
+		mcp.WithNumber("delta_y", mcp.Description("Vertical scroll delta in pixels. Default 300.")),
+	)
+}
+
+func (d *deps) handleScroll(_ context.Context, _ mcp.CallToolRequest, a scrollArgs) (*mcp.CallToolResult, error) {
+	deltaY := a.DeltaY
+	if deltaY == 0 && a.DeltaX == 0 {
+		deltaY = 300
+	}
+	err := d.withConn(portOr(a.Port), func(c *browser.CDPConn) error {
+		return browser.CdpScroll(c, a.DeltaX, deltaY)
+	})
+	if err != nil {
+		return mcp.NewToolResultError(err.Error()), nil
+	}
+	return mcp.NewToolResultText("scrolled"), nil
+}
+
+// ---- handle_dialog (MUTA) ----
+
+type handleDialogArgs struct {
+	Port       int    `json:"port"`
+	Accept     bool   `json:"accept"`
+	PromptText string `json:"prompt_text"`
+}
+
+func handleDialogTool() mcp.Tool {
+	return mcp.NewTool("handle_dialog",
+		mcp.WithDescription("Arm an auto-handler that responds to every JS dialog (alert/confirm/prompt/beforeunload) on the tab until disconnect. The handler lives in the pooled connection."),
+		mcp.WithNumber("port", mcp.Description("CDP port. Default 9222.")),
+		mcp.WithBoolean("accept", mcp.DefaultBool(true), mcp.Description("Whether to accept (true) or dismiss (false) dialogs. Default true.")),
+		mcp.WithString("prompt_text", mcp.Description("Text to enter for prompt() dialogs.")),
+	)
+}
+
+func (d *deps) handleHandleDialog(_ context.Context, _ mcp.CallToolRequest, a handleDialogArgs) (*mcp.CallToolResult, error) {
+	port := portOr(a.Port)
+	c, err := d.pool.get(port)
+	if err != nil {
+		return mcp.NewToolResultError(err.Error()), nil
+	}
+	cancel, err := browser.CdpHandleDialog(c, a.Accept, a.PromptText)
+	if err != nil {
+		return mcp.NewToolResultError(err.Error()), nil
+	}
+	d.pool.setCancel(port, cancel)
+	return mcp.NewToolResultText("dialog auto-handler armed"), nil
+}