cremote/mcp/main.go

2177 lines
64 KiB
Go

package main
import (
"context"
"encoding/json"
"fmt"
"log"
"os"
"strconv"
"time"
"git.teamworkapps.com/shortcut/cremote/client"
"github.com/mark3labs/mcp-go/mcp"
"github.com/mark3labs/mcp-go/server"
)
const Version = "2.0.0"
// CremoteServer wraps the cremote client for MCP
type CremoteServer struct {
client *client.Client
currentTab string
tabHistory []string
iframeMode bool
screenshots []string
}
// NewCremoteServer creates a new cremote MCP server
func NewCremoteServer(host string, port int) *CremoteServer {
return &CremoteServer{
client: client.NewClient(host, port),
tabHistory: make([]string, 0),
screenshots: make([]string, 0),
}
}
// Helper functions for parameter extraction
func getStringParam(params map[string]any, key, defaultValue string) string {
if val, ok := params[key].(string); ok {
return val
}
return defaultValue
}
func getBoolParam(params map[string]any, key string, defaultValue bool) bool {
if val, ok := params[key].(bool); ok {
return val
}
return defaultValue
}
func getIntParam(params map[string]any, key string, defaultValue int) int {
if val, ok := params[key].(float64); ok {
return int(val)
}
if val, ok := params[key].(int); ok {
return val
}
return defaultValue
}
func main() {
// Get cremote daemon connection settings
cremoteHost := os.Getenv("CREMOTE_HOST")
if cremoteHost == "" {
cremoteHost = "localhost"
}
cremotePortStr := os.Getenv("CREMOTE_PORT")
cremotePort := 8989
if cremotePortStr != "" {
if p, err := strconv.Atoi(cremotePortStr); err == nil {
cremotePort = p
}
}
log.Printf("Starting cremote MCP server, connecting to cremote daemon at %s:%d", cremoteHost, cremotePort)
// Create the cremote server
cremoteServer := NewCremoteServer(cremoteHost, cremotePort)
// Create MCP server
mcpServer := server.NewMCPServer("cremote-mcp", "2.0.0")
// Register version tool
mcpServer.AddTool(mcp.Tool{
Name: "version_cremotemcp",
Description: "Get version information for MCP server and daemon",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{},
Required: []string{},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Get daemon version
daemonVersion, err := cremoteServer.client.GetVersion()
if err != nil {
daemonVersion = fmt.Sprintf("Unable to connect: %v", err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("MCP Server version: %s\nDaemon version: %s", Version, daemonVersion)),
},
IsError: false,
}, nil
})
// Register web_navigate tool
mcpServer.AddTool(mcp.Tool{
Name: "web_navigate_cremotemcp",
Description: "Navigate to a URL and optionally take a screenshot",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"url": map[string]any{
"type": "string",
"description": "URL to navigate to",
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
"screenshot": map[string]any{
"type": "boolean",
"description": "Take screenshot after navigation",
},
},
Required: []string{"url"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
url := getStringParam(params, "url", "")
if url == "" {
return nil, fmt.Errorf("url parameter is required")
}
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
takeScreenshot := getBoolParam(params, "screenshot", false)
// If no tab specified and no current tab, create a new one
if tab == "" {
newTab, err := cremoteServer.client.OpenTab(timeout)
if err != nil {
return nil, fmt.Errorf("failed to create new tab: %w", err)
}
tab = newTab
cremoteServer.currentTab = tab
cremoteServer.tabHistory = append(cremoteServer.tabHistory, tab)
}
// Load the URL
err := cremoteServer.client.LoadURL(tab, url, timeout)
if err != nil {
return nil, fmt.Errorf("failed to load URL: %w", err)
}
message := fmt.Sprintf("Successfully navigated to %s in tab %s", url, tab)
// Take screenshot if requested
if takeScreenshot {
screenshotPath := fmt.Sprintf("/tmp/navigate-%d.png", time.Now().Unix())
err = cremoteServer.client.TakeScreenshot(tab, screenshotPath, false, timeout)
if err == nil {
cremoteServer.screenshots = append(cremoteServer.screenshots, screenshotPath)
message += fmt.Sprintf(" (screenshot saved to %s)", screenshotPath)
}
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(message),
},
IsError: false,
}, nil
})
// Register web_interact tool
mcpServer.AddTool(mcp.Tool{
Name: "web_interact_cremotemcp",
Description: "Interact with web elements (click, fill, submit)",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"action": map[string]any{
"type": "string",
"description": "Action to perform",
"enum": []any{"click", "fill", "submit", "upload", "select"},
},
"selector": map[string]any{
"type": "string",
"description": "CSS selector for the element",
},
"value": map[string]any{
"type": "string",
"description": "Value to fill (for fill/upload actions)",
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
},
Required: []string{"action", "selector"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
action := getStringParam(params, "action", "")
selector := getStringParam(params, "selector", "")
value := getStringParam(params, "value", "")
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
if action == "" {
return nil, fmt.Errorf("action parameter is required")
}
if selector == "" {
return nil, fmt.Errorf("selector parameter is required")
}
if tab == "" {
return nil, fmt.Errorf("no tab available - navigate to a page first")
}
var err error
var message string
switch action {
case "click":
err = cremoteServer.client.ClickElement(tab, selector, timeout)
message = fmt.Sprintf("Clicked element %s", selector)
case "fill":
if value == "" {
return nil, fmt.Errorf("value parameter is required for fill action")
}
err = cremoteServer.client.FillFormField(tab, selector, value, timeout)
message = fmt.Sprintf("Filled element %s with value", selector)
case "submit":
err = cremoteServer.client.SubmitForm(tab, selector, timeout)
message = fmt.Sprintf("Submitted form %s", selector)
case "upload":
if value == "" {
return nil, fmt.Errorf("value parameter (file path) is required for upload action")
}
err = cremoteServer.client.UploadFile(tab, selector, value, timeout)
message = fmt.Sprintf("Uploaded file %s to element %s", value, selector)
case "select":
if value == "" {
return nil, fmt.Errorf("value parameter is required for select action")
}
err = cremoteServer.client.SelectElement(tab, selector, value, timeout)
message = fmt.Sprintf("Selected option %s in element %s", value, selector)
default:
return nil, fmt.Errorf("unknown action: %s", action)
}
if err != nil {
return nil, fmt.Errorf("failed to %s element: %w", action, err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(message),
},
IsError: false,
}, nil
})
// Register web_extract tool
mcpServer.AddTool(mcp.Tool{
Name: "web_extract_cremotemcp",
Description: "Extract data from the page (source, element HTML, or execute JavaScript)",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"type": map[string]any{
"type": "string",
"description": "Type of extraction",
"enum": []any{"source", "element", "javascript"},
},
"selector": map[string]any{
"type": "string",
"description": "CSS selector (for element type)",
},
"code": map[string]any{
"type": "string",
"description": "JavaScript code (for javascript type)",
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
},
Required: []string{"type"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
extractType := getStringParam(params, "type", "")
selector := getStringParam(params, "selector", "")
code := getStringParam(params, "code", "")
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
if extractType == "" {
return nil, fmt.Errorf("type parameter is required")
}
if tab == "" {
return nil, fmt.Errorf("no tab available - navigate to a page first")
}
var data string
var err error
switch extractType {
case "source":
data, err = cremoteServer.client.GetPageSource(tab, timeout)
case "element":
if selector == "" {
return nil, fmt.Errorf("selector parameter is required for element extraction")
}
data, err = cremoteServer.client.GetElementHTML(tab, selector, timeout)
case "javascript":
if code == "" {
return nil, fmt.Errorf("code parameter is required for javascript extraction")
}
data, err = cremoteServer.client.EvalJS(tab, code, timeout)
default:
return nil, fmt.Errorf("unknown extraction type: %s", extractType)
}
if err != nil {
return nil, fmt.Errorf("failed to extract %s: %w", extractType, err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Extracted %s data: %s", extractType, data)),
},
IsError: false,
}, nil
})
// Register web_screenshot tool
mcpServer.AddTool(mcp.Tool{
Name: "web_screenshot_cremotemcp",
Description: "Take a screenshot of the current page",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"output": map[string]any{
"type": "string",
"description": "Output file path",
},
"full_page": map[string]any{
"type": "boolean",
"description": "Capture full page",
"default": false,
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
},
Required: []string{"output"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
output := getStringParam(params, "output", "")
fullPage := getBoolParam(params, "full_page", false)
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
if output == "" {
return nil, fmt.Errorf("output parameter is required")
}
if tab == "" {
return nil, fmt.Errorf("no tab available - navigate to a page first")
}
err := cremoteServer.client.TakeScreenshot(tab, output, fullPage, timeout)
if err != nil {
return nil, fmt.Errorf("failed to take screenshot: %w", err)
}
cremoteServer.screenshots = append(cremoteServer.screenshots, output)
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Screenshot saved to %s", output)),
},
IsError: false,
}, nil
})
// Register web_manage_tabs tool
mcpServer.AddTool(mcp.Tool{
Name: "web_manage_tabs_cremotemcp",
Description: "Manage browser tabs (open, close, list, switch)",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"action": map[string]any{
"type": "string",
"description": "Action to perform",
"enum": []any{"open", "close", "list", "switch"},
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (for close/switch actions)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
},
Required: []string{"action"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
action := getStringParam(params, "action", "")
tab := getStringParam(params, "tab", "")
timeout := getIntParam(params, "timeout", 5)
if action == "" {
return nil, fmt.Errorf("action parameter is required")
}
var err error
var message string
switch action {
case "open":
newTab, err := cremoteServer.client.OpenTab(timeout)
if err != nil {
return nil, fmt.Errorf("failed to open new tab: %w", err)
}
cremoteServer.currentTab = newTab
cremoteServer.tabHistory = append(cremoteServer.tabHistory, newTab)
message = fmt.Sprintf("Opened new tab: %s", newTab)
case "close":
if tab == "" {
return nil, fmt.Errorf("tab parameter is required for close action")
}
err = cremoteServer.client.CloseTab(tab, timeout)
if err != nil {
return nil, fmt.Errorf("failed to close tab: %w", err)
}
// Remove from history and update current tab
for i, id := range cremoteServer.tabHistory {
if id == tab {
cremoteServer.tabHistory = append(cremoteServer.tabHistory[:i], cremoteServer.tabHistory[i+1:]...)
break
}
}
if cremoteServer.currentTab == tab {
if len(cremoteServer.tabHistory) > 0 {
cremoteServer.currentTab = cremoteServer.tabHistory[len(cremoteServer.tabHistory)-1]
} else {
cremoteServer.currentTab = ""
}
}
message = fmt.Sprintf("Closed tab: %s", tab)
case "list":
tabs, err := cremoteServer.client.ListTabs()
if err != nil {
return nil, fmt.Errorf("failed to list tabs: %w", err)
}
message = fmt.Sprintf("Found %d tabs: %v", len(tabs), tabs)
case "switch":
if tab == "" {
return nil, fmt.Errorf("tab parameter is required for switch action")
}
cremoteServer.currentTab = tab
// Add to history if not already there
found := false
for _, t := range cremoteServer.tabHistory {
if t == tab {
found = true
break
}
}
if !found {
cremoteServer.tabHistory = append(cremoteServer.tabHistory, tab)
}
message = fmt.Sprintf("Switched to tab: %s", tab)
default:
return nil, fmt.Errorf("unknown tab action: %s", action)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(message),
},
IsError: false,
}, nil
})
// Register web_iframe tool
mcpServer.AddTool(mcp.Tool{
Name: "web_iframe_cremotemcp",
Description: "Switch iframe context for subsequent operations",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"action": map[string]any{
"type": "string",
"description": "Action to perform",
"enum": []any{"enter", "exit"},
},
"selector": map[string]any{
"type": "string",
"description": "Iframe CSS selector (for enter action)",
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
},
Required: []string{"action"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
action := getStringParam(params, "action", "")
selector := getStringParam(params, "selector", "")
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
if action == "" {
return nil, fmt.Errorf("action parameter is required")
}
if tab == "" {
return nil, fmt.Errorf("no tab available - navigate to a page first")
}
var err error
var message string
switch action {
case "enter":
if selector == "" {
return nil, fmt.Errorf("selector parameter is required for enter action")
}
err = cremoteServer.client.SwitchToIframe(tab, selector, timeout)
cremoteServer.iframeMode = true
message = fmt.Sprintf("Entered iframe: %s", selector)
case "exit":
err = cremoteServer.client.SwitchToMain(tab, timeout)
cremoteServer.iframeMode = false
message = "Exited iframe context"
default:
return nil, fmt.Errorf("unknown iframe action: %s", action)
}
if err != nil {
return nil, fmt.Errorf("failed to %s iframe: %w", action, err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(message),
},
IsError: false,
}, nil
})
// Register file_upload tool
mcpServer.AddTool(mcp.Tool{
Name: "file_upload_cremotemcp",
Description: "Upload a file from the client to the container for use in form uploads",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"local_path": map[string]any{
"type": "string",
"description": "Path to the file on the client machine",
},
"container_path": map[string]any{
"type": "string",
"description": "Optional path where to store the file in the container (defaults to /tmp/filename)",
},
},
Required: []string{"local_path"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
localPath := getStringParam(params, "local_path", "")
containerPath := getStringParam(params, "container_path", "")
if localPath == "" {
return nil, fmt.Errorf("local_path parameter is required")
}
// Upload the file to the container
targetPath, err := cremoteServer.client.UploadFileToContainer(localPath, containerPath)
if err != nil {
return nil, fmt.Errorf("failed to upload file: %w", err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("File uploaded successfully to container at: %s", targetPath)),
},
IsError: false,
}, nil
})
// Register file_download tool
mcpServer.AddTool(mcp.Tool{
Name: "file_download_cremotemcp",
Description: "Download a file from the container to the client (e.g., downloaded files from browser)",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"container_path": map[string]any{
"type": "string",
"description": "Path to the file in the container",
},
"local_path": map[string]any{
"type": "string",
"description": "Path where to save the file on the client machine",
},
},
Required: []string{"container_path", "local_path"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
containerPath := getStringParam(params, "container_path", "")
localPath := getStringParam(params, "local_path", "")
if containerPath == "" {
return nil, fmt.Errorf("container_path parameter is required")
}
if localPath == "" {
return nil, fmt.Errorf("local_path parameter is required")
}
// Download the file from the container
err := cremoteServer.client.DownloadFileFromContainer(containerPath, localPath)
if err != nil {
return nil, fmt.Errorf("failed to download file: %w", err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("File downloaded successfully from container to: %s", localPath)),
},
IsError: false,
}, nil
})
// Register console_logs tool
mcpServer.AddTool(mcp.Tool{
Name: "console_logs_cremotemcp",
Description: "Get console logs from the browser tab",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab)",
},
"clear": map[string]any{
"type": "boolean",
"description": "Clear logs after retrieval (default: false)",
"default": false,
},
},
Required: []string{},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
tab := getStringParam(params, "tab", cremoteServer.currentTab)
clear := getBoolParam(params, "clear", false)
// Get console logs
logs, err := cremoteServer.client.GetConsoleLogs(tab, clear)
if err != nil {
return nil, fmt.Errorf("failed to get console logs: %w", err)
}
// Format logs for display
var logText string
if len(logs) == 0 {
logText = "No console logs found."
} else {
logText = fmt.Sprintf("Found %d console log entries:\n\n", len(logs))
for i, log := range logs {
level := log["level"].(string)
message := log["message"].(string)
timestamp := log["timestamp"].(string)
logText += fmt.Sprintf("[%d] %s [%s]: %s\n", i+1, timestamp, level, message)
}
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(logText),
},
IsError: false,
}, nil
})
// Register console_command tool
mcpServer.AddTool(mcp.Tool{
Name: "console_command_cremotemcp",
Description: "Execute a command in the browser console",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"command": map[string]any{
"type": "string",
"description": "JavaScript command to execute in console",
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds (default: 5)",
"default": 5,
},
},
Required: []string{"command"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
command := getStringParam(params, "command", "")
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
if command == "" {
return nil, fmt.Errorf("command parameter is required")
}
// Execute console command using existing EvalJS functionality
result, err := cremoteServer.client.EvalJS(tab, command, timeout)
if err != nil {
return nil, fmt.Errorf("failed to execute console command: %w", err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Console command executed successfully.\nCommand: %s\nResult: %s", command, result)),
},
IsError: false,
}, nil
})
// Register web_element_check tool
mcpServer.AddTool(mcp.Tool{
Name: "web_element_check_cremotemcp",
Description: "Check existence, visibility, enabled state, count elements",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"selector": map[string]any{
"type": "string",
"description": "CSS selector for the element(s)",
},
"check_type": map[string]any{
"type": "string",
"description": "Type of check to perform",
"enum": []any{"exists", "visible", "enabled", "focused", "selected", "all"},
"default": "exists",
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
},
Required: []string{"selector"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
selector := getStringParam(params, "selector", "")
checkType := getStringParam(params, "check_type", "exists")
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
if selector == "" {
return nil, fmt.Errorf("selector parameter is required")
}
if tab == "" {
return nil, fmt.Errorf("no tab available - navigate to a page first")
}
result, err := cremoteServer.client.CheckElement(tab, selector, checkType, timeout)
if err != nil {
return nil, fmt.Errorf("failed to check element: %w", err)
}
// Format result as JSON string for display
resultJSON, _ := json.Marshal(result)
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Element check result: %s", string(resultJSON))),
},
IsError: false,
}, nil
})
// Register web_element_attributes tool
mcpServer.AddTool(mcp.Tool{
Name: "web_element_attributes_cremotemcp",
Description: "Get attributes, properties, computed styles of an element",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"selector": map[string]any{
"type": "string",
"description": "CSS selector for the element",
},
"attributes": map[string]any{
"type": "string",
"description": "Comma-separated list of attributes or 'all' for common attributes. Use 'style_' prefix for computed styles, 'prop_' for JavaScript properties",
"default": "all",
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
},
Required: []string{"selector"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
selector := getStringParam(params, "selector", "")
attributes := getStringParam(params, "attributes", "all")
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
if selector == "" {
return nil, fmt.Errorf("selector parameter is required")
}
if tab == "" {
return nil, fmt.Errorf("no tab available - navigate to a page first")
}
result, err := cremoteServer.client.GetElementAttributes(tab, selector, attributes, timeout)
if err != nil {
return nil, fmt.Errorf("failed to get element attributes: %w", err)
}
// Format result as JSON string for display
resultJSON, _ := json.Marshal(result)
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Element attributes: %s", string(resultJSON))),
},
IsError: false,
}, nil
})
// Register web_extract_multiple tool
mcpServer.AddTool(mcp.Tool{
Name: "web_extract_multiple_cremotemcp",
Description: "Extract from multiple selectors in one call",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"selectors": map[string]any{
"type": "object",
"description": "Object with keys as labels and values as CSS selectors",
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
},
Required: []string{"selectors"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
selectorsParam := params["selectors"]
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
if selectorsParam == nil {
return nil, fmt.Errorf("selectors parameter is required")
}
if tab == "" {
return nil, fmt.Errorf("no tab available - navigate to a page first")
}
// Convert selectors to map[string]string
selectorsMap := make(map[string]string)
if selectorsObj, ok := selectorsParam.(map[string]any); ok {
for key, value := range selectorsObj {
if selector, ok := value.(string); ok {
selectorsMap[key] = selector
}
}
} else {
return nil, fmt.Errorf("selectors must be an object with string values")
}
result, err := cremoteServer.client.ExtractMultiple(tab, selectorsMap, timeout)
if err != nil {
return nil, fmt.Errorf("failed to extract multiple: %w", err)
}
// Format result as JSON string for display
resultJSON, _ := json.Marshal(result)
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Multiple extraction result: %s", string(resultJSON))),
},
IsError: false,
}, nil
})
// Register web_extract_links tool
mcpServer.AddTool(mcp.Tool{
Name: "web_extract_links_cremotemcp",
Description: "Extract all links with filtering options",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"container_selector": map[string]any{
"type": "string",
"description": "Optional CSS selector to limit search to a container",
},
"href_pattern": map[string]any{
"type": "string",
"description": "Optional regex pattern to filter links by href",
},
"text_pattern": map[string]any{
"type": "string",
"description": "Optional regex pattern to filter links by text content",
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
},
Required: []string{},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
containerSelector := getStringParam(params, "container_selector", "")
hrefPattern := getStringParam(params, "href_pattern", "")
textPattern := getStringParam(params, "text_pattern", "")
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
if tab == "" {
return nil, fmt.Errorf("no tab available - navigate to a page first")
}
result, err := cremoteServer.client.ExtractLinks(tab, containerSelector, hrefPattern, textPattern, timeout)
if err != nil {
return nil, fmt.Errorf("failed to extract links: %w", err)
}
// Format result as JSON string for display
resultJSON, _ := json.Marshal(result)
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Links extraction result: %s", string(resultJSON))),
},
IsError: false,
}, nil
})
// Register web_extract_table tool
mcpServer.AddTool(mcp.Tool{
Name: "web_extract_table_cremotemcp",
Description: "Extract table data as structured JSON",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"selector": map[string]any{
"type": "string",
"description": "CSS selector for the table element",
},
"include_headers": map[string]any{
"type": "boolean",
"description": "Whether to extract and use headers for structured data",
"default": true,
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
},
Required: []string{"selector"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
selector := getStringParam(params, "selector", "")
includeHeaders := getBoolParam(params, "include_headers", true)
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
if selector == "" {
return nil, fmt.Errorf("selector parameter is required")
}
if tab == "" {
return nil, fmt.Errorf("no tab available - navigate to a page first")
}
result, err := cremoteServer.client.ExtractTable(tab, selector, includeHeaders, timeout)
if err != nil {
return nil, fmt.Errorf("failed to extract table: %w", err)
}
// Format result as JSON string for display
resultJSON, _ := json.Marshal(result)
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Table extraction result: %s", string(resultJSON))),
},
IsError: false,
}, nil
})
// Register web_extract_text tool
mcpServer.AddTool(mcp.Tool{
Name: "web_extract_text_cremotemcp",
Description: "Extract text with pattern matching",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"selector": map[string]any{
"type": "string",
"description": "CSS selector for elements to extract text from",
},
"pattern": map[string]any{
"type": "string",
"description": "Optional regex pattern to match within text",
},
"extract_type": map[string]any{
"type": "string",
"description": "Type of text extraction",
"enum": []any{"text", "innerText", "textContent"},
"default": "textContent",
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
},
Required: []string{"selector"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
selector := getStringParam(params, "selector", "")
pattern := getStringParam(params, "pattern", "")
extractType := getStringParam(params, "extract_type", "textContent")
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
if selector == "" {
return nil, fmt.Errorf("selector parameter is required")
}
if tab == "" {
return nil, fmt.Errorf("no tab available - navigate to a page first")
}
result, err := cremoteServer.client.ExtractText(tab, selector, pattern, extractType, timeout)
if err != nil {
return nil, fmt.Errorf("failed to extract text: %w", err)
}
// Format result as JSON string for display
resultJSON, _ := json.Marshal(result)
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Text extraction result: %s", string(resultJSON))),
},
IsError: false,
}, nil
})
// Register web_form_analyze tool
mcpServer.AddTool(mcp.Tool{
Name: "web_form_analyze_cremotemcp",
Description: "Analyze forms completely",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"selector": map[string]any{
"type": "string",
"description": "CSS selector for the form element",
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
},
Required: []string{"selector"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
selector := getStringParam(params, "selector", "")
if selector == "" {
return nil, fmt.Errorf("selector parameter is required")
}
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
result, err := cremoteServer.client.AnalyzeForm(tab, selector, timeout)
if err != nil {
return nil, fmt.Errorf("failed to analyze form: %w", err)
}
resultJSON, err := json.MarshalIndent(result, "", " ")
if err != nil {
return nil, fmt.Errorf("failed to marshal result: %w", err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Form analysis result: %s", string(resultJSON))),
},
IsError: false,
}, nil
})
// Register web_interact_multiple tool
mcpServer.AddTool(mcp.Tool{
Name: "web_interact_multiple_cremotemcp",
Description: "Batch interactions",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"interactions": map[string]any{
"type": "array",
"description": "Array of interactions to perform",
"items": map[string]any{
"type": "object",
"properties": map[string]any{
"selector": map[string]any{
"type": "string",
"description": "CSS selector for the element",
},
"action": map[string]any{
"type": "string",
"description": "Action to perform",
"enum": []any{"click", "fill", "select", "check", "uncheck"},
},
"value": map[string]any{
"type": "string",
"description": "Value for the action (required for fill, select)",
},
},
"required": []string{"selector", "action"},
},
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
},
Required: []string{"interactions"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
interactionsData, ok := params["interactions"].([]any)
if !ok {
return nil, fmt.Errorf("interactions parameter is required and must be an array")
}
// Parse interactions
var interactions []client.InteractionItem
for _, interactionData := range interactionsData {
interactionMap, ok := interactionData.(map[string]any)
if !ok {
return nil, fmt.Errorf("each interaction must be an object")
}
interaction := client.InteractionItem{}
if selector, ok := interactionMap["selector"].(string); ok {
interaction.Selector = selector
} else {
return nil, fmt.Errorf("each interaction must have a selector")
}
if action, ok := interactionMap["action"].(string); ok {
interaction.Action = action
} else {
return nil, fmt.Errorf("each interaction must have an action")
}
if value, ok := interactionMap["value"].(string); ok {
interaction.Value = value
}
interactions = append(interactions, interaction)
}
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
result, err := cremoteServer.client.InteractMultiple(tab, interactions, timeout)
if err != nil {
return nil, fmt.Errorf("failed to perform multiple interactions: %w", err)
}
resultJSON, err := json.MarshalIndent(result, "", " ")
if err != nil {
return nil, fmt.Errorf("failed to marshal result: %w", err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Multiple interactions result: %s", string(resultJSON))),
},
IsError: false,
}, nil
})
// Register web_form_fill_bulk tool
mcpServer.AddTool(mcp.Tool{
Name: "web_form_fill_bulk_cremotemcp",
Description: "Fill entire forms with key-value pairs",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"fields": map[string]any{
"type": "object",
"description": "Map of field names/selectors to values",
},
"form_selector": map[string]any{
"type": "string",
"description": "CSS selector for the form element (optional)",
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
},
Required: []string{"fields"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
fieldsData, ok := params["fields"].(map[string]any)
if !ok {
return nil, fmt.Errorf("fields parameter is required and must be an object")
}
// Convert fields to map[string]string
fields := make(map[string]string)
for key, value := range fieldsData {
if strValue, ok := value.(string); ok {
fields[key] = strValue
} else {
return nil, fmt.Errorf("all field values must be strings")
}
}
formSelector := getStringParam(params, "form_selector", "")
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
result, err := cremoteServer.client.FillFormBulk(tab, formSelector, fields, timeout)
if err != nil {
return nil, fmt.Errorf("failed to fill form bulk: %w", err)
}
resultJSON, err := json.MarshalIndent(result, "", " ")
if err != nil {
return nil, fmt.Errorf("failed to marshal result: %w", err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Form bulk fill result: %s", string(resultJSON))),
},
IsError: false,
}, nil
})
// Register web_page_info tool
mcpServer.AddTool(mcp.Tool{
Name: "web_page_info_cremotemcp",
Description: "Get comprehensive page metadata and state information",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab if not specified)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds (default: 5)",
"default": 5,
},
},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
tabID := getStringParam(params, "tab", "")
timeout := getIntParam(params, "timeout", 5)
result, err := cremoteServer.client.GetPageInfo(tabID, timeout)
if err != nil {
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Error getting page info: %v", err)),
},
IsError: true,
}, nil
}
resultJSON, err := json.MarshalIndent(result, "", " ")
if err != nil {
return nil, fmt.Errorf("failed to marshal result: %w", err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Page info: %s", string(resultJSON))),
},
IsError: false,
}, nil
})
// Register web_viewport_info tool
mcpServer.AddTool(mcp.Tool{
Name: "web_viewport_info_cremotemcp",
Description: "Get viewport and scroll information",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab if not specified)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds (default: 5)",
"default": 5,
},
},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
tabID := getStringParam(params, "tab", "")
timeout := getIntParam(params, "timeout", 5)
result, err := cremoteServer.client.GetViewportInfo(tabID, timeout)
if err != nil {
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Error getting viewport info: %v", err)),
},
IsError: true,
}, nil
}
resultJSON, err := json.MarshalIndent(result, "", " ")
if err != nil {
return nil, fmt.Errorf("failed to marshal result: %w", err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Viewport info: %s", string(resultJSON))),
},
IsError: false,
}, nil
})
// Register web_performance_metrics tool
mcpServer.AddTool(mcp.Tool{
Name: "web_performance_metrics_cremotemcp",
Description: "Get page performance metrics",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab if not specified)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds (default: 5)",
"default": 5,
},
},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
tabID := getStringParam(params, "tab", "")
timeout := getIntParam(params, "timeout", 5)
result, err := cremoteServer.client.GetPerformance(tabID, timeout)
if err != nil {
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Error getting performance metrics: %v", err)),
},
IsError: true,
}, nil
}
resultJSON, err := json.MarshalIndent(result, "", " ")
if err != nil {
return nil, fmt.Errorf("failed to marshal result: %w", err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Performance metrics: %s", string(resultJSON))),
},
IsError: false,
}, nil
})
// Register web_content_check tool
mcpServer.AddTool(mcp.Tool{
Name: "web_content_check_cremotemcp",
Description: "Check for specific content types and loading states",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"type": map[string]any{
"type": "string",
"description": "Content type to check",
"enum": []any{"images", "scripts", "styles", "forms", "links", "iframes", "errors"},
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab if not specified)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds (default: 5)",
"default": 5,
},
},
Required: []string{"type"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
contentType := getStringParam(params, "type", "")
if contentType == "" {
return nil, fmt.Errorf("type parameter is required")
}
tabID := getStringParam(params, "tab", "")
timeout := getIntParam(params, "timeout", 5)
result, err := cremoteServer.client.CheckContent(tabID, contentType, timeout)
if err != nil {
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Error checking content: %v", err)),
},
IsError: true,
}, nil
}
resultJSON, err := json.MarshalIndent(result, "", " ")
if err != nil {
return nil, fmt.Errorf("failed to marshal result: %w", err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Content check result: %s", string(resultJSON))),
},
IsError: false,
}, nil
})
// Phase 5: Enhanced Screenshot and File Management Tools
// web_screenshot_element_cremotemcp - Screenshot specific elements
mcpServer.AddTool(mcp.Tool{
Name: "web_screenshot_element_cremotemcp",
Description: "Take a screenshot of a specific element on the page",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"selector": map[string]any{
"type": "string",
"description": "CSS selector for the element to screenshot",
},
"output": map[string]any{
"type": "string",
"description": "Path where to save the screenshot",
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab if not specified)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds (default: 5)",
},
},
Required: []string{"selector", "output"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
selector := getStringParam(params, "selector", "")
output := getStringParam(params, "output", "")
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
if selector == "" {
return nil, fmt.Errorf("selector parameter is required")
}
if output == "" {
return nil, fmt.Errorf("output parameter is required")
}
if tab == "" {
return nil, fmt.Errorf("no tab available - navigate to a page first")
}
err := cremoteServer.client.ScreenshotElement(tab, selector, output, timeout)
if err != nil {
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Error taking element screenshot: %v", err)),
},
IsError: true,
}, nil
}
cremoteServer.screenshots = append(cremoteServer.screenshots, output)
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Element screenshot saved to: %s", output)),
},
IsError: false,
}, nil
})
// web_screenshot_enhanced_cremotemcp - Enhanced screenshots with metadata
mcpServer.AddTool(mcp.Tool{
Name: "web_screenshot_enhanced_cremotemcp",
Description: "Take an enhanced screenshot with metadata (timestamp, viewport size, URL)",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"output": map[string]any{
"type": "string",
"description": "Path where to save the screenshot",
},
"full_page": map[string]any{
"type": "boolean",
"description": "Capture full page (default: false)",
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab if not specified)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds (default: 5)",
},
},
Required: []string{"output"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
output := getStringParam(params, "output", "")
fullPage := getBoolParam(params, "full_page", false)
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
if output == "" {
return nil, fmt.Errorf("output parameter is required")
}
if tab == "" {
return nil, fmt.Errorf("no tab available - navigate to a page first")
}
metadata, err := cremoteServer.client.ScreenshotEnhanced(tab, output, fullPage, timeout)
if err != nil {
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Error taking enhanced screenshot: %v", err)),
},
IsError: true,
}, nil
}
cremoteServer.screenshots = append(cremoteServer.screenshots, output)
metadataJSON, err := json.MarshalIndent(metadata, "", " ")
if err != nil {
return nil, fmt.Errorf("failed to marshal metadata: %w", err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Enhanced screenshot saved with metadata:\n%s", string(metadataJSON))),
},
IsError: false,
}, nil
})
// file_operations_bulk_cremotemcp - Bulk file operations
mcpServer.AddTool(mcp.Tool{
Name: "file_operations_bulk_cremotemcp",
Description: "Perform bulk file operations (upload/download multiple files)",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"operation": map[string]any{
"type": "string",
"description": "Operation type",
"enum": []any{"upload", "download"},
},
"files": map[string]any{
"type": "array",
"description": "Array of file operations",
"items": map[string]any{
"type": "object",
"properties": map[string]any{
"local_path": map[string]any{
"type": "string",
"description": "Path on client machine",
},
"container_path": map[string]any{
"type": "string",
"description": "Path in container",
},
"operation": map[string]any{
"type": "string",
"description": "Override operation type for this file",
"enum": []any{"upload", "download"},
},
},
"required": []any{"local_path", "container_path"},
},
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds (default: 30)",
},
},
Required: []string{"operation", "files"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
operation := getStringParam(params, "operation", "")
filesParam := params["files"]
timeout := getIntParam(params, "timeout", 30)
if operation == "" {
return nil, fmt.Errorf("operation parameter is required")
}
if filesParam == nil {
return nil, fmt.Errorf("files parameter is required")
}
// Convert files parameter to FileOperation slice
filesArray, ok := filesParam.([]any)
if !ok {
return nil, fmt.Errorf("files must be an array")
}
var operations []client.FileOperation
for _, fileItem := range filesArray {
fileMap, ok := fileItem.(map[string]any)
if !ok {
return nil, fmt.Errorf("each file must be an object")
}
localPath := getStringParam(fileMap, "local_path", "")
containerPath := getStringParam(fileMap, "container_path", "")
fileOperation := getStringParam(fileMap, "operation", operation)
if localPath == "" || containerPath == "" {
return nil, fmt.Errorf("local_path and container_path are required for each file")
}
operations = append(operations, client.FileOperation{
LocalPath: localPath,
ContainerPath: containerPath,
Operation: fileOperation,
})
}
result, err := cremoteServer.client.BulkFiles(operation, operations, timeout)
if err != nil {
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Error performing bulk file operations: %v", err)),
},
IsError: true,
}, nil
}
resultJSON, err := json.MarshalIndent(result, "", " ")
if err != nil {
return nil, fmt.Errorf("failed to marshal result: %w", err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Bulk file operations completed:\n%s", string(resultJSON))),
},
IsError: false,
}, nil
})
// file_management_cremotemcp - File management operations
mcpServer.AddTool(mcp.Tool{
Name: "file_management_cremotemcp",
Description: "Manage files (cleanup, list, get info)",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"operation": map[string]any{
"type": "string",
"description": "Management operation",
"enum": []any{"cleanup", "list", "info"},
},
"pattern": map[string]any{
"type": "string",
"description": "File pattern for cleanup/list, or file path for info",
},
"max_age": map[string]any{
"type": "string",
"description": "Max age in hours for cleanup (default: 24)",
},
},
Required: []string{"operation"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
// Convert arguments to map
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
operation := getStringParam(params, "operation", "")
pattern := getStringParam(params, "pattern", "")
maxAge := getStringParam(params, "max_age", "")
if operation == "" {
return nil, fmt.Errorf("operation parameter is required")
}
result, err := cremoteServer.client.ManageFiles(operation, pattern, maxAge)
if err != nil {
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("Error managing files: %v", err)),
},
IsError: true,
}, nil
}
resultJSON, err := json.MarshalIndent(result, "", " ")
if err != nil {
return nil, fmt.Errorf("failed to marshal result: %w", err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(fmt.Sprintf("File management result:\n%s", string(resultJSON))),
},
IsError: false,
}, nil
})
// Accessibility tree tools
mcpServer.AddTool(mcp.Tool{
Name: "get_accessibility_tree_cremotemcp",
Description: "Get the full accessibility tree for a page or with limited depth",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab)",
},
"depth": map[string]any{
"type": "integer",
"description": "Maximum depth to retrieve (optional, omit for full tree)",
"minimum": 0,
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
},
Required: []string{},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
// Parse depth parameter
var depth *int
if depthParam := getIntParam(params, "depth", -1); depthParam >= 0 {
depth = &depthParam
}
result, err := cremoteServer.client.GetAccessibilityTree(tab, depth, timeout)
if err != nil {
return nil, fmt.Errorf("failed to get accessibility tree: %w", err)
}
resultJSON, err := json.MarshalIndent(result, "", " ")
if err != nil {
return nil, fmt.Errorf("failed to marshal result: %w", err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(string(resultJSON)),
},
IsError: false,
}, nil
})
mcpServer.AddTool(mcp.Tool{
Name: "get_partial_accessibility_tree_cremotemcp",
Description: "Get accessibility tree for a specific element and its relatives",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"selector": map[string]any{
"type": "string",
"description": "CSS selector for the target element",
},
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab)",
},
"fetch_relatives": map[string]any{
"type": "boolean",
"description": "Whether to fetch ancestors, siblings, and children",
"default": true,
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
},
Required: []string{"selector"},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
selector := getStringParam(params, "selector", "")
if selector == "" {
return nil, fmt.Errorf("selector parameter is required")
}
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
fetchRelatives := getBoolParam(params, "fetch_relatives", true)
result, err := cremoteServer.client.GetPartialAccessibilityTree(tab, selector, fetchRelatives, timeout)
if err != nil {
return nil, fmt.Errorf("failed to get partial accessibility tree: %w", err)
}
resultJSON, err := json.MarshalIndent(result, "", " ")
if err != nil {
return nil, fmt.Errorf("failed to marshal result: %w", err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(string(resultJSON)),
},
IsError: false,
}, nil
})
mcpServer.AddTool(mcp.Tool{
Name: "query_accessibility_tree_cremotemcp",
Description: "Query accessibility tree for nodes matching specific criteria",
InputSchema: mcp.ToolInputSchema{
Type: "object",
Properties: map[string]any{
"tab": map[string]any{
"type": "string",
"description": "Tab ID (optional, uses current tab)",
},
"selector": map[string]any{
"type": "string",
"description": "CSS selector to limit search scope (optional)",
},
"accessible_name": map[string]any{
"type": "string",
"description": "Accessible name to match (optional)",
},
"role": map[string]any{
"type": "string",
"description": "ARIA role to match (optional)",
},
"timeout": map[string]any{
"type": "integer",
"description": "Timeout in seconds",
"default": 5,
},
},
Required: []string{},
},
}, func(ctx context.Context, request mcp.CallToolRequest) (*mcp.CallToolResult, error) {
params, ok := request.Params.Arguments.(map[string]any)
if !ok {
return nil, fmt.Errorf("invalid arguments format")
}
tab := getStringParam(params, "tab", cremoteServer.currentTab)
timeout := getIntParam(params, "timeout", 5)
selector := getStringParam(params, "selector", "")
accessibleName := getStringParam(params, "accessible_name", "")
role := getStringParam(params, "role", "")
// At least one search criteria must be provided
if selector == "" && accessibleName == "" && role == "" {
return nil, fmt.Errorf("at least one search criteria (selector, accessible_name, or role) must be provided")
}
result, err := cremoteServer.client.QueryAccessibilityTree(tab, selector, accessibleName, role, timeout)
if err != nil {
return nil, fmt.Errorf("failed to query accessibility tree: %w", err)
}
resultJSON, err := json.MarshalIndent(result, "", " ")
if err != nil {
return nil, fmt.Errorf("failed to marshal result: %w", err)
}
return &mcp.CallToolResult{
Content: []mcp.Content{
mcp.NewTextContent(string(resultJSON)),
},
IsError: false,
}, nil
})
// Start the server
log.Printf("Cremote MCP server ready")
if err := server.ServeStdio(mcpServer); err != nil {
log.Fatalf("Server error: %v", err)
}
}