// SCAN REPORT

School MCP

9 tools. 3 can modify or destroy data without limits.

3 write tools that can modify data. Rate limits recommended.

Last updated: 27 Sept 2026

3 can modify or destroy data

6 read-only

9 tools total

Community server · catalogue entry checked 23/09/2026

How to control School MCP ↓

TOOL MAP

What School MCP exposes to your agents

Read (6) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous School MCP tools

Write · Medium add_to_reminders The tool creates new data (reminder entries) in the user's macOS Reminders app. Write · Low set_download_path This tool modifies a user preference/setting by updating the default download directory. Write · High switch_school_account Modifies application state by changing authenticated account context; affects all subsequent operations and persists system-wide.

3 of School MCP's 9 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control School MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and School MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "add_to_reminders": {
    "limits": [
      {
        "counter": "add_to_reminders_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "download_course_files": {
    "limits": [
      {
        "counter": "download_course_files_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register School MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON SCHOOL →

Instant setup, no code required.

FULL CATALOGUE

All 9 School MCP tools

WRITE 3 tools

Write add_to_reminders Add upcoming deadlines to macOS Reminders. Write set_download_path Set the default download path for Canvas files. Write switch_school_account Switch the active school account. Persists across restarts.

READ 6 tools

Read download_course_files download_course_files Read get_deadlines Get upcoming deadlines from Canvas and Gradescope. Read get_download_path_info Get the current default download path for Canvas files. Read list_course_files list_course_files Read list_courses List available courses from Canvas. Read list_school_accounts List the configured school accounts (e.g. columbia, mit) and show which one is active.

FAQ

Questions about School MCP

How do I prevent bulk modifications through School MCP? +

The School MCP server has 3 write tools including add_to_reminders, set_download_path, switch_school_account. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach School MCP.

How many tools does the School MCP server expose? +

9 tools across 2 categories: Read, Write. 6 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on School MCP? +

Register the School MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every School MCP tool call.

Deterministic rules across all 9 School MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SCHOOL →

Instant setup, no code required.

9 School MCP tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from School's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →