Google Classroom MCP Server
LocalAbout Google Classroom MCP Server
Google Classroom MCP Server gives MCP-compatible AI assistants access to Google Classroom course data. It is for users who want to query courses, announcements, and coursework through an assistant, using Google OAuth authentication.
Key features
- 01List all courses
- 02View course details and announcements
- 03Retrieve assignments and submissions
- 04Authenticate with Google OAuth
Use cases
- 01Review courses in Google Classroom
- 02Check a course’s announcements and details
- 03Inspect coursework and submissions
MCP support
The MCP server exposes courses, course-details, and assignments tools to compatible clients for reading Google Classroom data.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEGoogle Classroom MCP Server
An MCP (Model Context Protocol) server that provides access to Google Classroom data through Claude and other AI assistants that support the MCP protocol.
Setup
Prerequisites
- Node.js (v16 or higher)
- A Google Cloud Platform project with the Google Classroom API enabled
- OAuth 2.0 client credentials for the Google Classroom API
Installation
Installing via Smithery
To install Google Classroom MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @faizan45640/google-classroom-mcp-server --client claude
Installing Manually
- Clone this repository
- Install dependencies:
npm install
- Place your Google OAuth client credentials in a file named
credentials.jsonin the project root:
{
"web": {
"client_id": "YOUR_CLIENT_ID",
"project_id": "YOUR_PROJECT_ID",
"auth_uri": "https://accounts.google.com/o/oauth2/auth",
"token_uri": "https://oauth2.googleapis.com/token",
"auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
"client_secret": "YOUR_CLIENT_SECRET",
"redirect_uris": ["http://localhost:3000/auth/google/callback"]
}
}
- Authenticate with Google:
node index.js auth
This will launch a browser window to complete the OAuth flow and save your credentials to tokens.json.
- Configure Claude to use this server by updating
claude_desktop_config.json(typically in%APPDATA%\Claude\):
{
"mcpServers": {
"class": {
"command": "node",
"args": [
"PATH_TO_YOUR_DIRECTORY\\index.js"
]
}
}
}
Usage
Available Tools
The server provides several tools for interacting with Google Classroom:
1. courses - List all your Google Classroom courses
Use the 'courses' tool to get a list of all your Google Classroom courses
2. course-details - Get detailed information about a specific course
Use the 'course-details' tool with the courseId parameter to get details and announcements for a specific course
Parameters:
courseId: The ID of the course (can be obtained from thecoursestool)
3. assignments - Get assignments for a specific course
Use the 'assignments' tool with the courseId parameter to get assignments and your submissions for a specific course
Parameters:
courseId: The ID of the course (can be obtained from thecoursestool)
Example Prompts for Claude
- Show me all my Google Classroom courses
- Get details for my Math course with ID 123456789
- Show me all assignments for my History course with ID 987654321
Permissions
The server requests the following Google Classroom API permissions:
classroom.courses.readonly- To access course informationclassroom.announcements.readonly- To access course announcementsclassroom.coursework.me.readonly- To access your coursework and assignmentsclassroom.rosters.readonly- To access class rosters
Troubleshooting
If you encounter permission errors, try:
-
Running the auth command again to refresh permissions:
node index.js auth -
Ensuring your Google account is added as a test user in the Google Cloud Console if your app is in testing mode
-
Checking the OAuth scopes in the
authenticateAndSaveCredentialsfunction to ensure they match your needs
Notes
- This server is designed to be used with Claude AI or other MCP-compatible assistants
- All API requests are made using your authenticated Google account
- Token refresh is handled automatically by the server
- Sensitive credentials are stored locally in the
tokens.jsonfile
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
