Connector Β· Learning management system

Google Classroom MCP Server & Agent Skill

Last updated

ibl.ai publishes a free Google Classroom agent skill: a SKILL.md that teaches an AI agent to read and write Google Classroom data and expose it as an MCP tool. Download it, connect your own Google Classroom credentials, and run the agent on ibl.ai Agentic OS, where you own all the code and the data.

Google Classroom is Google Workspace for Education's class tool. It holds courses, teacher and student rosters, guardians, coursework, student submissions and grades, announcements and topics.

What is the Google Classroom API, and what can an agent read from it?

Create, read and modify courses, rosters (students, teachers, invitations, guardians), coursework, course materials, topics, announcements and student submissions, including grading and returning work. Push notifications are available.

  • API: Google Classroom API (REST)
  • Access: Public, self-serve
  • Base URL: https://classroom.googleapis.com/v1/
  • Authentication: OAuth 2.0 authorization code

Any developer can call the API from a Google Cloud project with OAuth credentials. Rubrics, grading periods and add-on attachments need users with certain Google Workspace for Education licenses.

OAuth 2.0 with Classroom scopes such as classroom.courses, classroom.rosters.readonly, classroom.coursework.students and classroom.student-submissions.students.readonly (prefix https://www.googleapis.com/auth/).

What can an agent read from Google Classroom?

  • Courses β€” courses.list and courses.get return courses the user can access.
  • Rosters β€” courses.students.list and courses.teachers.list return a course's students and teachers.
  • Coursework β€” courses.courseWork.list/get return assignments and questions.
  • Student submissions β€” courses.courseWork.studentSubmissions.list/get return submission state and grades.
  • Announcements and topics β€” Course announcements and topics, under the announcements and topics scopes.
  • Guardians β€” Guardian links for students, under the guardianlinks scopes.

What can an agent write to Google Classroom?

  • Courses and coursework β€” courses.create/patch and courses.courseWork.create/patch create or edit courses and assignments.
  • Grades and returned work β€” studentSubmissions.patch sets grades; studentSubmissions.return returns work to the student. Confirm with the user first.
  • Roster changes β€” courses.students.create/delete and courses.teachers.create/delete add or remove people. Confirm with the user first.
  • Deletions β€” courses.delete and courses.courseWork.delete remove a course or assignment. Confirm with the user first.
  • Announcements β€” Post announcements to a course stream (classroom.announcements scope). Confirm with the user first.

Limits: Per 60-second moving average: 4,000,000 queries/day per client, 3,000/minute per client and 1,200/minute per user. Over quota returns RESOURCE_EXHAUSTED; request increases in the Google Cloud console.

Student education records protected by FERPA: rosters, guardian contacts, submitted work and grades. Accounts are usually district-managed Google Workspace for Education users.

How do I connect Google Classroom to an AI agent over MCP?

Google publishes an official MCP server: Google Classroom MCP server (classroommcp.googleapis.com).

Google's remote MCP endpoint https://classroommcp.googleapis.com/mcp/v1 with 16 tools (courses, coursework, rubrics, topics, announcements). Requires the Workspace Developer Preview Program.

You can register that server on ibl.ai as it is, or use the SKILL.md below when you want the agent to call the Google Classroom API directly.

On ibl.ai an MCP connection is three records, and a working integration always needs all three:

  1. Register the server β€” POST …/mcp-servers/ with its URL, a transport (sse, websocket or streamable_http) and an auth_type of none, token or oauth2.
  2. Create a connection that holds the credential, scoped to the whole organization (platform), to a single agent, or to each user (user).
  3. Enable it on the agent β€” mcp-tool in tool_slugs and the server id in mcp_servers. Both lists are replaced, not merged, so read the settings first.

Google Classroom supports per-user OAuth, so the server can use auth_type=oauth2 with auth_scope=user: each person connects their own Google Classroom account in the chat the first time the agent needs it.

The field reference is in MCP server connections, and the /iblai-api-agent-mcp skill runs all three steps from a coding agent.

What does the Google Classroom agent skill do?

The Google Classroom skill is one SKILL.md file named iblai-connect-google-classroom. It gives an agent the auth conventions, what to read, which writes need a person's confirmation, the ibl.ai MCP wiring, example prompts and guardrails.

Download the Google Classroom SKILL.md

Save it as .claude/skills/iblai-connect-google-classroom/SKILL.md, or in your agent's skills folder. The ibl.ai platform skills it calls come from one install:

$ npx skills add iblai/vibe --all

This connector skill is a starting point maintained on ibl.ai, not part of the iblai/vibe repository.

It was checked against Google's documentation on October 20, 2026. Test it against your own Google Classroom setup before you rely on it.

What can I ask a Google Classroom agent to do?

  • β€œList my Google Classroom courses and how many students are in each”
  • β€œShow which students haven't turned in the Week 6 essay in Period 4 English”
  • β€œCreate a short-answer assignment due Friday in all my 8th-grade science classes”
  • β€œGrade and return the submissions for the lab report using these scores”

How do I run a Google Classroom agent on ibl.ai?

Agentic OS is where the agent runs on ibl.ai: it holds the Google Classroom MCP connection, the model the agent uses, its instructions and its conversation history.

On ibl.ai you own all the code and the data, run it model-agnostic across any LLM, and pay with no per-seat pricing β€” so you can deploy anywhere, from your own cloud to a fully air-gapped network.

Which ibl.ai agents work with Google Classroom data?

Which ibl.ai platform skills does a Google Classroom agent use?

  • /iblai-api-agent-mcp β€” MCP connectors for ibl.ai agents, end to end
  • /iblai-vibe-agent-mcp β€” Add the agent MCP tab (Model Context Protocol connector management with featured connectors, custom connectors, OAuth,…
  • /iblai-api-agent-tool β€” Enable or disable an ibl.ai agent's tools via the platform API

What else should I know before connecting Google Classroom to an AI agent?

Is there an official Google Classroom MCP server?

Yes. Google publishes Google Classroom MCP server (classroommcp.googleapis.com).

You can register it on ibl.ai as an MCP server, or use the SKILL.md when you want the agent to call the Google Classroom API directly.

Who can get Google Classroom API credentials?

Any developer can call the API from a Google Cloud project with OAuth credentials. Rubrics, grading periods and add-on attachments need users with certain Google Workspace for Education licenses.

Does Google Classroom data leave my infrastructure when an ibl.ai agent uses it?

On ibl.ai, you own all the code and the data. Self-hosted in your cloud or data center, the agent, its MCP connections and its conversation logs stay inside your perimeter.

Because the platform is model-agnostic, you can point the agent at a model you host, so Google Classroom records need not reach a third-party model provider.

Is the Google Classroom agent skill free to use?

Yes. The SKILL.md is a free download with no sign-up. It assumes you already have Google Classroom credentials, and your agreement with Google still governs how you use its API.

Which other data sources can an AI agent connect to alongside Google Classroom?

Which other K-12 systems have a connector?

Every connector, grouped by sector, is on the connectors hub.