Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
tabs_listA

List open browser tabs.

tab_selectC

Make a tab active by tabId.

tab_newA

Open a NEW tab (optionally at a URL) and focus it. Prefer this over navigate when the user says "open"/"go to" a site — navigate REPLACES the current tab. Pass active:false to open in the background (used by parallel batches).

tab_closeB

Close a tab by tabId.

navigateA

Navigate a tab to a URL, REPLACING its current page. Acts on the active tab unless tabId is given — to open a site without losing the current page, use tab_new instead.

backB

Go back in history.

forwardC

Go forward in history.

reloadA

Reload the active (or given) tab.

clickA

Click an element (target by selector or a snapshot ref). trusted=true uses real OS-level input.

typeB

Type text into an element. trusted=true sends real keystrokes (works on React/Vue controlled inputs).

select_optionC

Select option(s) of a by value or visible label.

pressC

Press a key (with optional modifiers).

hoverC

Hover over an element.

scrollC

Scroll the page or to an element.

screenshotC

Capture a PNG screenshot (page or element).

get_textA

Get visible text of the page or an element.

get_htmlC

Get HTML of the page or an element.

snapshotC

Accessibility snapshot: interactive elements with stable refs to target by ref (more reliable than guessing CSS selectors).

get_cookiesB

Read cookies visible to the tab's URL (or a given url).

storageC

Read/write localStorage (or sessionStorage). op: get|set|remove|clear.

evalC

Evaluate JavaScript in the page (disabled in safe-mode).

wait_forC

Wait for a selector or text to appear/disappear.

extract_linksC

Extract anchors from the page or a subtree.

read_as_markdownC

Read the page (or subtree) as readable markdown.

fill_formC

Fill multiple fields (keyed by selector) and optionally submit.

download_fileB

Download a file by URL or from a link element.

upload_fileA

Set local file(s) on a file (target by selector or ref) — uploads without the OS dialog. Requires --enable-uploads. files are absolute local paths.

chrome_statusB

Report backend/session status.

profile_useA

Switch the active browser profile (identity). Subsequent downloads, results, screenshots, and the action log are stored under profiles//. Resets the active task to "default" unless you then call task_new.

task_newA

Start a new task (run) under the active profile. Creates profiles//tasks// with downloads/, results/, screenshots/ and makes it the active task so all captured artifacts land there.

tasks_listA

List every task across all profiles under the data dir, with sizes and download counts.

task_statusA

Report the active profile/task and the folder paths where this run's artifacts are stored.

batchA

Run multiple tool calls in one request — parallel (default) or serial. Each op is { tool, args } and goes through the same policy gate, rate limit, and error handling as a direct call. In parallel mode, tab-scoped ops MUST pass an explicit tabId (the active-tab default is unsafe under concurrency). Use to drive several tabs at once (e.g. open tabs, then batch get_text across them). Cannot be nested.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Mehmoodqureshi/chrome-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server