relay-inspect
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CDP_WS_URL | No | Connect directly to a CDP WebSocket URL, skipping Chrome discovery | |
| CHROME_PATH | No | Override Chrome/Chromium executable path (auto-detect if empty) | |
| CHROME_DEBUG_HOST | No | Chrome debugging host | localhost |
| CHROME_DEBUG_PORT | No | Chrome debugging port | 9222 |
| CHROME_LAUNCH_URL | No | URL to open when Chrome is auto-launched (e.g. http://localhost:1420) | |
| CHROME_AUTO_LAUNCH | No | Auto-launch Chrome if not already running | true |
| CONSOLE_BUFFER_SIZE | No | Max console entries to buffer | 500 |
| NETWORK_BUFFER_SIZE | No | Max network requests to buffer | 200 |
| SERVER_LOG_BUFFER_SIZE | No | Max log entries per managed server | 1000 |
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_connectionA | Check Chrome DevTools connection status and diagnose issues (does not auto-launch Chrome) |
| connect_to_pageB | Connect to a specific Chrome page target by ID or URL pattern. |
| evaluate_jsB | Execute a JavaScript expression in the browser and return the result |
| get_console_logsB | Return buffered console output (logs, warnings, errors) from the browser |
| get_network_requestsC | Return captured network requests and responses from the browser |
| get_elementsA | Query the DOM with a CSS selector and return matching elements' outer HTML |
| wait_and_checkA | Wait N seconds then return new console output captured during the wait (useful after page reload) |
| take_screenshotB | Capture a screenshot of the current page |
| reload_pageA | Reload the current page (optionally bypass cache) |
| navigate_toB | Navigate the current page to a new URL |
| get_network_request_detailA | Get full request and response body for a specific network request by ID |
| start_serverB | Start a dev server or background process and capture its output |
| get_server_logsB | Read stdout/stderr output from a managed server process |
| stop_serverA | Stop a running managed server process |
| list_serversA | List all managed server processes and their status |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 15 tools
Each tool has a clearly distinct purpose: browser connection, navigation, DOM inspection, console/network logs, screenshots, and server management. No two tools overlap in functionality, so an agent can reliably select the correct tool.
All tool names follow a consistent verb_noun snake_case pattern (e.g., evaluate_js, get_console_logs, take_screenshot). The pattern is uniform and predictable across the entire set.
With 15 tools, the set covers the browser inspection and server management domain comprehensively without being bloated. Each tool serves a necessary function, and the count feels well-scoped.
The tool set covers the full lifecycle of browser inspection (connect, navigate, evaluate, capture, logs, network) and server management (start, stop, list, logs). Any missing actions (e.g., clicking elements) can be achieved via evaluate_js, so there are no critical gaps.