Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
BROWSER_CHANNELNoBrowser channel (e.g., chrome, msedge)
BROWSER_TIMEOUTNoDefault timeout in ms30000
BROWSER_HEADLESSNoRun browser in headed modetrue
BROWSER_SESSIONS_DIRNoDirectory for screenshots and sessions.browser-sessions
BROWSER_VIEWPORT_WIDTHNoBrowser viewport width1280
BROWSER_VIEWPORT_HEIGHTNoBrowser viewport height720
BROWSER_SECURITY_PROFILENoSecurity profile (local-dev, restricted, open)local-dev

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
browser_navigateD–
browser_go_backD–
browser_go_forwardD–
browser_clickD–
browser_typeD–
browser_hoverD–
browser_dragD–
browser_select_optionD–
browser_press_keyD–
browser_scrollD–
browser_screenshotD–
browser_snapshotD–
browser_console_messagesD–
browser_network_requestsD–
browser_evaluateD–
browser_tab_listD–
browser_tab_newD–
browser_tab_selectD–
browser_closeD–
test_scenario_runD–
test_scenario_statusD–
test_assertD–
test_fill_formD–
test_auth_flowD–
test_watch_eventsD–
test_stop_watchD–
session_startD–
session_endD–
session_listD–
session_replayD–
visual_baselineD–
visual_compareD–

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

C2/5.0

Scored across 32 tools

Disambiguation4/5

Tool names are mostly distinct, with browser_* and test_* prefixes clearly separating categories. However, some potential overlap exists between browser_screenshot and browser_snapshot, and test_fill_form could be confused with browser_type. Overall, the names are specific enough for an agent to differentiate.

Naming Consistency5/5

All tools follow a consistent pattern of prefix_object_action (e.g., browser_navigate, test_scenario_run, session_start). This uniformity makes the set predictable and easy to navigate.

Tool Count4/5

With 32 tools, the count is high but appropriate for a comprehensive browser automation and testing server. Each tool seems justified given the domain (browser control, testing, sessions, visual checks), though a slight reduction could improve simplicity.

Completeness4/5

The tool surface covers major browser interactions, testing scenarios, session management, and visual comparisons. Missing elements like network mocking or cookie management are notable, but core workflows appear well-supported.

Maintenance

ActivityInactive
ResponsivenessUnresponsive