Classroom Browser MCP
A read-only MCP server that automates Google Classroom web pages for accounts without OAuth access, enabling search and reading of courses, classwork, and attachments.
README
Classroom Browser MCP
A local, read-only MCP server for Google Classroom accounts that cannot grant OAuth access to the official Classroom API. It automates the same Classroom web pages you can already open and stores the browser session only in a dedicated local profile.
This is specifically for users who cannot use Google Cloud Platform (for any reason) or use their google account to sign in to unauthorised services (specifically students under DETNSW).
What it exposes
classroom_auth_statusclassroom_find_assessment- searches Classwork and Stream posts, expands matching items, and reads attached PDFs/Google Docsclassroom_search_activity- searches posts and Classwork, expands comments, and distinguishes direct teacher replies from related teacher-posted resourcesclassroom_list_coursesclassroom_list_classworkclassroom_get_classworkclassroom_search_classwork
There are deliberately no submission, comment, upload, or deletion tools.
Setup
npm install
npm run login
An Edge window opens. Sign in with the school account, verify Classroom loads, and close the window. Then build the server:
npm run build
npm run verify
npm run verify -- "Assessment Task 4 Advanced"
Add it to an MCP client using this command (replace the path if needed):
{
"mcpServers": {
"google-classroom": {
"command": "node",
"args": ["D:\\classroom-mcp\\dist\\server.js"]
}
}
}
Configuration
Environment variables are optional:
| Variable | Default | Purpose |
|---|---|---|
CLASSROOM_PROFILE_DIR |
~/.classroom-browser-mcp |
Dedicated browser profile location |
CLASSROOM_BROWSER_CHANNEL |
msedge |
Playwright browser channel, such as chrome or msedge |
CLASSROOM_BROWSER_EXECUTABLE |
unset | Exact browser executable path; overrides the channel |
CLASSROOM_LOCALE |
en-AU |
Browser locale |
Limits and privacy
This is UI automation, not an undocumented Google API. It can break when Classroom changes its page structure, and your school's policies still apply. The browser profile contains session cookies, so keep it private. Credentials are entered directly into Google's page and are never read or stored by this project.
MCP calls are always headless. Only npm run login opens a visible window for the one-time Google sign-in.
Only use it with an account and coursework you are authorized to access. If the school explicitly forbids browser automation, do not use it without permission.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.