// MCP TOOL REFERENCE

LOOKING GLASS TOOLS

71 tools from the Looking Glass MCP Server, categorised by risk level.

View the Looking Glass policy → Token cost: 5,080 tokens →
// ALL 71 LOOKING GLASS TOOLS
READ 45 tools
Read browser_action_history browser_action_history Read browser_analyze_page browser_analyze_page Read browser_clean_slate browser_clean_slate Read browser_console_messages browser_console_messages Read browser_diagnose browser_diagnose Read browser_diff_state browser_diff_state Read browser_error_report browser_error_report Read browser_evaluate browser_evaluate Read browser_explore browser_explore Read browser_extract browser_extract Read browser_get_cookies browser_get_cookies Read browser_get_localstorage browser_get_localstorage Read browser_go browser_go Read browser_go_back browser_go_back Read browser_go_forward browser_go_forward Read browser_health_check browser_health_check Read browser_hover browser_hover Read browser_list_mocks browser_list_mocks Read browser_mock_route browser_mock_route Read browser_network_requests browser_network_requests Read browser_recover browser_recover Read browser_screenshot browser_screenshot Read browser_snapshot browser_snapshot Read browser_snapshot_state browser_snapshot_state Read browser_suggest_actions browser_suggest_actions Read browser_tab_list browser_tab_list Read browser_workflow browser_workflow Read session_end session_end Read session_list session_list Read session_replay session_replay Read test_accessibility_audit test_accessibility_audit Read test_assert test_assert Read test_auth_flow test_auth_flow Read test_chaos test_chaos Read test_chaos_clear test_chaos_clear Read test_fill_form test_fill_form Read test_generate_assertions test_generate_assertions Read test_scenario_run test_scenario_run Read test_scenario_status test_scenario_status Read test_stop_watch test_stop_watch Read test_watch_events test_watch_events Read vault_inject vault_inject Read vault_list vault_list Read visual_baseline visual_baseline Read visual_compare visual_compare
WRITE 16 tools
Write browser_click browser_click Write browser_close browser_close Write browser_drag browser_drag Write browser_fill_and_submit browser_fill_and_submit Write browser_login browser_login Write browser_press_key browser_press_key Write browser_resolve_element browser_resolve_element Write browser_scroll browser_scroll Write browser_select_option browser_select_option Write browser_set_cookie browser_set_cookie Write browser_set_localstorage browser_set_localstorage Write browser_smart_click browser_smart_click Write browser_tab_select browser_tab_select Write browser_type browser_type Write session_export_playwright session_export_playwright Write vault_login vault_login
DESTRUCTIVE 4 tools
Destructive browser_clear_history browser_clear_history Destructive browser_clear_mocks browser_clear_mocks Destructive browser_clear_storage browser_clear_storage Destructive vault_delete vault_delete
EXECUTE 6 tools
Execute browser_navigate browser_navigate Execute browser_performance_audit browser_performance_audit Execute browser_tab_new browser_tab_new Execute browser_wait_for browser_wait_for Execute browser_wait_until_stable browser_wait_until_stable Execute session_start session_start
// RUNNING THIS SERVER

The managed route: connect Looking Glass through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y looking-glass-mcp
// FAQ
How many tools does the Looking Glass MCP server have? +

The Looking Glass MCP server exposes 71 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Looking Glass tools? +

Route the Looking Glass server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Looking Glass tools fall into? +

Looking Glass tools are categorised as Read (45), Write (16), Destructive (4), Execute (6). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.