Skip to main content
Glama

Google Classroom MCP (local)

This MCP server exposes multiple tools for read + write:

  • classroom_get_user_enrollments

  • classroom_get_course

  • classroom_list_courses

  • classroom_create_course

  • classroom_update_course

  • classroom_set_course_state

  • classroom_archive_course

  • classroom_activate_course

  • classroom_delete_course

  • classroom_list_course_students

  • classroom_list_course_teachers

  • classroom_add_teacher_to_course

  • classroom_remove_teacher_from_course

  • classroom_add_student_to_course

  • classroom_remove_student_from_course

  • classroom_list_invitations

  • classroom_get_invitation

  • classroom_create_invitation

  • classroom_delete_invitation

  • classroom_accept_invitation

  • classroom_list_course_topics

  • classroom_create_topic

  • classroom_create_announcement

  • classroom_list_coursework_materials

  • classroom_create_coursework_material

  • classroom_list_coursework

  • classroom_create_assignment

  • classroom_clone_course

  • classroom_list_student_submissions

  • classroom_set_draft_grade

  • classroom_set_assigned_grade

  • classroom_turn_in_submission

  • classroom_reclaim_submission

  • classroom_return_submission

1) Google Workspace setup

  1. Create (or choose) a Google Cloud project.

  2. Enable Google Classroom API.

  3. Create a Service Account and download its JSON key.

  4. Enable Domain-wide delegation on that service account.

  5. In Google Admin Console, go to Security > API controls > Domain-wide delegation and add:

    • Client ID: service account client ID

    • OAuth scopes (comma-separated):

      • https://www.googleapis.com/auth/classroom.courses.readonly

      • https://www.googleapis.com/auth/classroom.courses

      • https://www.googleapis.com/auth/classroom.rosters.readonly

      • https://www.googleapis.com/auth/classroom.rosters

      • https://www.googleapis.com/auth/classroom.profile.emails

      • https://www.googleapis.com/auth/classroom.topics.readonly

      • https://www.googleapis.com/auth/classroom.topics

      • https://www.googleapis.com/auth/classroom.announcements

      • https://www.googleapis.com/auth/classroom.coursework.students.readonly

      • https://www.googleapis.com/auth/classroom.coursework.students

      • https://www.googleapis.com/auth/classroom.coursework.me

      • https://www.googleapis.com/auth/classroom.courseworkmaterials.readonly

      • https://www.googleapis.com/auth/classroom.courseworkmaterials

  6. Ensure the delegated admin user can read Classroom data in your domain.

Related MCP server: Google Workspace MCP Server

2) Local install

cd /home/carlos/classroom-mcp
bash setup.sh
cp .env.example .env
# edit .env

Optional policy in .env:

CLASSROOM_REQUIRED_TEACHERS=osvalin15@certificacionmontessori.com,online@asociacionmontessori.mx
CLASSROOM_OBSOLETE_TEACHERS=presidencia@asociacionmontessori.mx

When set, these teachers are auto-added for:

  • classroom_create_course

  • classroom_clone_course

Obsolete filter behavior:

  • classroom_list_courses and classroom_get_user_enrollments exclude courses that include any teacher from CLASSROOM_OBSOLETE_TEACHERS.

  • If CLASSROOM_OBSOLETE_TEACHERS is not set, default exclusion is presidencia@asociacionmontessori.mx.

  • Set CLASSROOM_OBSOLETE_TEACHERS= (empty) to disable this filter.

3) Register in Codex

codex mcp add classroom -- /home/carlos/classroom-mcp/run.sh
codex mcp list

4) Example prompt in Codex

En qué materias está registrado el usuario guiarodrigo@asociacionmontessori.mx?

5) Smoke test (portable)

Run the full write-path smoke test with automatic cleanup:

cd /home/carlos/classroom-mcp
./smoke_test.sh

You can override inputs with flags:

./smoke_test.sh \
  --teacher-email carlos@certificacionmontessori.com \
  --student-email carlos@asociacionmontessori.com.mx \
  --course-id 765463029199

Or set defaults in .env:

  • SMOKE_TEST_TEACHER_EMAIL

  • SMOKE_TEST_STUDENT_EMAIL

  • SMOKE_TEST_COURSE_ID

Keep generated artifacts (no cleanup) only when debugging:

./smoke_test.sh --keep-artifacts

6) Admin smoke test (course lifecycle + invitations)

This covers the newer admin tools:

  • create/update/archive/activate/delete course

  • add/remove teacher

  • create/get/list/accept/delete invitation

cd /home/carlos/classroom-mcp
./admin_smoke_test.sh

With explicit inputs:

./admin_smoke_test.sh \
  --admin-email admin@asociacionmontessori.com.mx \
  --teacher-email carlos@certificacionmontessori.com \
  --student-email carlos@asociacionmontessori.com.mx

Defaults can live in .env:

  • ADMIN_SMOKE_ADMIN_EMAIL

  • ADMIN_SMOKE_TEACHER_EMAIL

  • ADMIN_SMOKE_STUDENT_EMAIL

7) Clone course example (MCP)

Use the new tool to clone structure + content safely as drafts:

classroom_clone_course(
  source_course_id="844288618274",
  new_course_name="Copia de F12 - Lenguaje",
  teacher_emails=["carlos@certificacionmontessori.com"],
  student_emails=["carlos@asociacionmontessori.com.mx"],
  copy_topics=true,
  copy_coursework=true,
  copy_coursework_materials=true,
  force_draft_for_created_work=true
)

Notes

  • If the user exists outside your Workspace domain, Google may return 403/404.

  • If you need archived courses too, ask with course_state="ARCHIVED".

  • acting_user_email lets you impersonate a teacher/admin for operations that require role-specific permissions.

  • classroom_create_announcement does not support real Classroom topic binding; if topic_id is sent, it is appended as text marker.

  • classroom_create_course defaults to PROVISIONED for safer setup before going live.

  • classroom_create_course defaults ownerId to acting_user_email (or GOOGLE_WORKSPACE_ADMIN_EMAIL) when not provided.

  • classroom_delete_course permanently deletes the course; prefer classroom_archive_course when in doubt.

  • classroom_clone_course creates a new course and can copy topics, coursework, and course work materials with optional teacher/student enrollment.

  • classroom_clone_course defaults force_draft_for_created_work=true to avoid publishing cloned content unexpectedly.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

  • The Google Compute Engine MCP server is a fully-managed Model Context Protocol server that provides tools to manage Google Compute Engine resources through AI agents. It enables capabilities including instance management (creating, starting, stopping, resetting, listing), disk management, handling instance templates and group managers, viewing machine and accelerator types, managing images, and accessing reservation and commitment information. The server operates as a zero-deployment, enterprise-grade endpoint at https://compute.googleapis.com/mcp with built-in IAM-based security.

  • The Google GKE MCP server is a managed Model Context Protocol server that provides AI applications with tools to manage Google Kubernetes Engine (GKE) clusters and Kubernetes resources. It exposes a structured, discoverable interface that allows AI agents to interact with GKE and Kubernetes APIs, enabling them to inspect cluster configurations, retrieve Kubernetes resource YAMLs, monitor operations like cluster upgrades, diagnose issues, and optimize costs—all without needing to parse text output or use complex kubectl commands.

  • The Manifold Markets MCP server provides comprehensive access to prediction market features, enabling users to create and manage markets, execute trades, and manage liquidity through a clean interface. It facilitates sophisticated market interactions with Manifold's platform, including market discovery, trading operations, information retrieval for users and portfolios, and social features like following markets and transferring mana.

  • The BigQuery remote MCP server is a fully managed service that uses the Model Context Protocol to connect AI applications and LLMs to BigQuery data sources. It provides secure, standardized tools for AI agents to list datasets and tables, retrieve schemas, generate and execute SQL queries through natural language, and analyze data—enabling direct access to enterprise analytics data without requiring manual SQL coding.

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/carlosrm22/mcp-classroom-codex'

If you have feedback or need assistance with the MCP directory API, please join our Discord server