Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
BU_CDP_URLNoCDP URL of an existing Chrome to drive instead of launching a new one.
JEV_RA_MODELNoOverride the model name.
JEV_RA_CHROMENoPath to the Chrome binary to launch.
JEV_RA_API_KEYNoAPI key for TypeSafe (direct). Highest precedence; used if set.
JEV_RA_ENDPOINTNoOverride the API endpoint.
JEV_RA_VIEWPORTNoViewport size, e.g. 1280x900.1280x900
JEV_RA_MAX_STEPSNoMaximum number of steps per run.40
JEV_RA_TIMEOUT_SNoTimeout in seconds.120
TYPESAFE_API_KEYNoTypeSafe API key. Used if JEV_RA_API_KEY is not set.
JEV_RA_SEARCH_URLNoSearch endpoint template; {query} is substituted.
JEV_RA_TEXT_MODELNoOptional text helper model name.
OPENROUTER_API_KEYNoOpenRouter API key (starts with sk-or-). Used if neither JEV_RA_API_KEY nor TYPESAFE_API_KEY is set.
JEV_RA_TEXT_API_KEYNoOptional text helper API key.
JEV_RA_MAX_DECISIONSNoMaximum number of decisions per run.80
JEV_RA_TEXT_BASE_URLNoOptional text helper base URL.
JEV_RA_BLOCK_RESOURCESNoSet to '0' to stop blocking fonts and media.1

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": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
browser_openB

Open a URL in the shared browser session and summarise the page.

browser_runC

Pursue a whole goal on the current page. Supply values for anything that must be typed.

browser_actD

Take one decided step towards an instruction on the current page.

browser_searchC

Search the web, read the best results in parallel tabs, and rank them against the goal.

browser_observeC

List the observed controls and the visible text of the current page.

browser_extractB

Pull structured page data from the DOM: text, elements, links, tables or main.

browser_clickB

Click one observed element by its ref.

browser_typeC

Type text into one observed field by its ref.

browser_selectC

Select an observed dropdown option by its value or label.

browser_scrollA

Scroll the page one viewport step up or down.

browser_pressB

Press Enter, Escape or Tab.

browser_waitB

Wait a moment and observe again.

browser_screenshotA

Capture the current viewport as a JPEG.

browser_closeA

Close the browser session held by this server.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3/5.0

Scored across 14 tools

Disambiguation4/5

Most tools are clearly distinct, but browser_act overlaps with browser_click/type/select/etc. as a generic 'take a step' action, and browser_run could be confused with act at a higher level. The descriptions help distinguish them, but an agent might occasionally misselect between generic and specific actions.

Naming Consistency5/5

All 14 tools follow the exact same browser_<verb> pattern using lowercase snake_case. The naming is highly predictable and consistent, making it easy to infer a tool's purpose from its prefix and verb.

Tool Count5/5

14 tools is a well-scoped count for a browser automation server, covering navigation, observation, interaction, and high-level task execution without being bloated. Each tool has a clear role in the workflow.

Completeness4/5

The surface covers the core browser lifecycle (open, observe, interact, navigate, close) and includes both low-level and high-level operations. Minor gaps like back/forward navigation or page refresh are missing, but agents can work around them using open or run.

Maintenance

ActivityMaintained
ResponsivenessNo issues