Chrome Course MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
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
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| chrome_launchB | Launch a Chrome window with the DevTools Protocol enabled, or open a new tab if it is already running. |
| chrome_open_tabA | Open a new tab through an existing Chrome DevTools Protocol endpoint. |
| chrome_tabsA | List Chrome tabs exposed by the local Chrome DevTools Protocol endpoint. |
| chrome_navigateB | Navigate the selected Chrome tab to a URL and wait briefly for the page to load. |
| chrome_snapshotB | Summarize the selected page with visible text, links, buttons, inputs, selects, and forms for automation planning. |
| chrome_clickB | Click an element by CSS selector or visible text. Useful for control panels and file-manager buttons. |
| chrome_typeC | Type into an input or textarea by CSS selector, label text, placeholder, name, id, or aria-label. |
| chrome_selectA | Set a select dropdown by CSS selector or label text, matching option value or visible text. |
| chrome_pressB | Send a keyboard key to the selected page, optionally after focusing an element. |
| chrome_screenshotC | Capture a PNG screenshot of the selected page. |
| chrome_evalB | Evaluate JavaScript in the selected tab. Use for small, explicit inspection or panel automation snippets. |
| chrome_extract_mediaC | Extract media, document, iframe, and link candidates from a selected Chrome tab. |
| chrome_save_pageC | Save the selected Chrome tab as HTML and/or PDF. |
| chrome_download_urlsC | Download authorized direct URLs using cookies from the selected Chrome tab. |
| brightspace_collect_currentC | Create a Brightspace-oriented manifest from the selected course/module page. |
| brightspace_archive_linksB | Navigate through Brightspace links from the current tab or a provided URL list and save each page as a categorized manifest plus HTML/PDF. |
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 16 tools
Most tools target distinct actions (open, navigate, click, type, screenshot, etc.), and the two Brightspace tools are clearly separate. Slight overlap exists between chrome_open_tab and chrome_launch, and between chrome_snapshot and chrome_extract_media, but descriptions resolve ambiguity.
All tools follow a consistent pattern: domain_verb_noun (chrome_*, brightspace_*). Every name uses lowercase with underscores and a clear action verb, making the naming predictable and easy to learn.
With 16 tools, the set is slightly above the ideal 3-15 range but still well-scoped for Chrome automation plus Brightspace-specific archiving. Each tool has a specific role, and the count feels justified rather than bloated.
The Chrome automation covers a full interaction lifecycle: tab management, navigation, reading, clicking, typing, selecting, pressing, evaluating, saving, downloading, and media extraction. Brightspace coverage is limited to collecting/archiving pages, which fits the apparent purpose but lacks other potential course-management operations.