Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

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
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
electron_setupA

Find an Electron app in /Applications and generate a launch command with debugging flags. Returns the exact command to run.

electron_connectB

Connect to a running Electron app on both CDP (renderer) and V8 Inspector (main process) ports.

chromeB

Connect to existing Chrome/Electron or launch a new Chrome instance with remote debugging.

chrome_list_connectionsA

List all active Chrome connections with their status.

chrome_switch_connectionB

Switch the active Chrome connection.

chrome_disconnectC

Disconnect from a Chrome instance.

targetB

List or switch browser targets (pages, workers).

query_elementsA

Find elements by CSS selector with DOM depth filtering. Returns tag, text, id, classes, visibility.

click_elementB

Click an element matching the CSS selector.

fill_elementB

Fill text into an input element matching the CSS selector.

navigateA

Navigate to a URL and wait for page load.

get_console_logsC

Get console log messages from the browser.

take_screenshotC

Capture a screenshot of the current page.

renderer_evaluateA

Evaluate arbitrary JavaScript in the renderer process. Does not require debugger pause.

v8_connectB

Connect to a V8 Inspector endpoint on a running Electron main process.

v8_evaluateC

Evaluate JavaScript in the Electron main process via V8 Inspector.

v8_disconnectB

Disconnect a V8 Inspector connection.

v8_list_connectionsA

List all V8 Inspector connections.

enable_networkB

Start capturing network requests for the current connection.

get_network_requestsB

List captured network requests with optional filtering.

clear_network_requestsC

Clear captured network requests.

enable_debug_toolsA

Enable JavaScript debugger. Must be called before breakpoints or stepping.

breakpointB

Set or remove breakpoints.

stepB

Step through code execution when paused.

executionC

Resume or pause execution.

call_stackA

Get the current call stack when execution is paused.

evaluateB

Evaluate JavaScript in a specific call frame. Only works when paused.

pause_on_exceptionsB

Configure whether to pause when exceptions are thrown.

helpA

Show install instructions for Electric Cherry across different tools.

hide_toolsB

Hide tools by pattern or specific names.

show_toolsB

Show (restore) hidden tools.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.1/5.0

Scored across 31 tools

Disambiguation3/5

Some tools overlap in purpose (electron_connect vs v8_connect vs chrome, renderer_evaluate vs evaluate), and generic names like 'target' and 'step' could be ambiguous. However, most tools have clear, distinct roles when read with descriptions, so the ambiguity is moderate.

Naming Consistency3/5

Many tools follow a context_action pattern (v8_connect, chrome_switch_connection), but there are also bare nouns (target, breakpoint, execution) and verbs (navigate, evaluate). The mixed conventions are readable but lack a single consistent pattern.

Tool Count2/5

With 31 tools, the surface is notably large, spanning connections, debugging, navigation, network, and evaluation. While each group covers a niche, the total feels excessive for typical agent workflows, and could be consolidated (e.g., merging v8_connect with electron_connect).

Completeness4/5

The tool set covers the core lifecycle of Electron debugging: setup, connect, navigate, interact, inspect, debug, and evaluate. Minor gaps exist such as no explicit wait-for-element or page source retrieval, but agents can work around these with evaluate.

Maintenance

ActivityInactive
ResponsivenessNo issues