# start_chrome Start Chrome with remote debugging enabled and optionally establish connection. Launches Chrome browser with DevTools Protocol debugging enabled on the specified port. Supports both headless and windowed modes, with automatic executable detection across platforms. Can optionally connect to the started instance and navigate to a specific URL in a single operation. The function handles existing Chrome instances gracefully, detecting if Chrome is already running on the target port and optionally connecting to it rather than attempting to start a new instance. Args: port: TCP port for Chrome remote debugging server (default: 9222). Must be available or already in use by Chrome. url: Initial URL to navigate to after starting Chrome. If provided, Chrome will load this page on startup. headless: Whether to run Chrome in headless mode without GUI. Useful for automated testing and server environments. chrome_path: Custom path to Chrome executable. If not provided, uses automatic detection based on platform. auto_connect: Whether to automatically connect to Chrome and enable debugging domains after startup. Returns: Comprehensive status dictionary containing: - success: Boolean indicating operation success - message: Human-readable status description - data: Detailed information including: - port: Port Chrome is running on - pid: Process ID of Chrome instance (if started) - connected: Whether connection was established - navigated: Whether URL navigation succeeded - alreadyRunning: Whether Chrome was already running Raises: The function handles exceptions internally and returns error responses rather than raising exceptions. Check the 'success' field in the response. Note: Uses a temporary user data directory to avoid conflicts with existing Chrome profiles. The directory location is platform-specific. Agent View of the PolicyLayer registry record for `start_chrome`. HTML page: https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/start-chrome ## Facts - Tool: `start_chrome` - Server: Chrome Devtools (`benjaminr/chrome-devtools-mcp`) — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp.md - Homepage: https://github.com/benjaminr/chrome-devtools-mcp - Risk category: Execute (High risk) - Registry record: grade F, identity unverified - Server rate-limited: no - Parameters: 0 - Recommended policy verdict: Rate-limited ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "start_chrome", "arguments": {} } } ``` ## Why start_chrome is rated High Starting Chrome with remote debugging enabled and establishing connections to control browser behavior constitutes executing external operations. While not directly destructive or financial, it enables arbitrary browser automation and code execution through the DevTools Protocol, making it an Execute-category tool. From the tool's own definition: "Tool 'start_chrome' launches Chrome browser with remote debugging enabled and can automatically connect to it." ## Use case AI agents invoke start_chrome to trigger actions in Chrome Devtools. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started. ## Recommended policy (PolicyLayer) Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Chrome Devtools: ```json { "version": "1", "default": "deny", "tools": { "start_chrome": { "limits": [ { "counter": "start_chrome_rate", "window": "minute", "max": 10, "scope": "grant" } ] } } } ``` ## Other tools on Chrome Devtools (46) - `clear_all_cookies` — Destructive — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/clear-all-cookies.md - `clear_storage_for_origin` — Destructive — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/clear-storage-for-origin.md - `clear_console` — Execute — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/clear-console.md - `connect_to_browser` — Execute — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/connect-to-browser.md - `evaluate_in_all_frames` — Execute — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/evaluate-in-all-frames.md - `execute_javascript` — Execute — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/execute-javascript.md - `focus_element` — Execute — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/focus-element.md - `inspect_console_object` — Execute — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/inspect-console-object.md - `navigate_to_url` — Execute — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/navigate-to-url.md - `override_storage_quota` — Execute — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/override-storage-quota.md - `start_chrome_and_connect` — Execute — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/start-chrome-and-connect.md - `start_css_coverage_tracking` — Execute — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/start-css-coverage-tracking.md - `track_indexeddb` — Execute — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/track-indexeddb.md - `disconnect_from_browser` — Other — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/disconnect-from-browser.md - `collect_css_class_names` — Read — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/collect-css-class-names.md - `describe_element` — Read — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/describe-element.md - `get_all_cookies` — Read — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/get-all-cookies.md - `get_background_colors` — Read — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/get-background-colors.md - `get_computed_styles` — Read — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/get-computed-styles.md - `get_connection_status` — Read — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/get-connection-status.md - `get_console_error_summary` — Read — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/get-console-error-summary.md - `get_console_logs` — Read — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/get-console-logs.md - `get_cookies` — Read — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/get-cookies.md - `get_document` — Read — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/get-document.md - `get_element_at_position` — Read — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/get-element-at-position.md - `get_element_attributes` — Read — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/get-element-attributes.md - `get_element_box_model` — Read — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/get-element-box-model.md - `get_element_outer_html` — Read — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/get-element-outer-html.md - `get_inline_styles` — Read — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/get-inline-styles.md - `get_matched_styles` — Read — https://policylayer.com/tools/benjaminr-chrome-devtools-mcp/get-matched-styles.md - …and 16 more: https://policylayer.com/tools/benjaminr-chrome-devtools-mcp.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=benjaminr-chrome-devtools-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/benjaminr-chrome-devtools-mcp