// SCAN REPORT

Leafeep

11 tools. 4 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

4 can modify or destroy data

7 read-only

11 tools total

Community server · catalogue entry verified 03/07/2026

How to control Leafeep ↓

TOOL MAP

What Leafeep exposes to your agents

Read (7) Write / Execute (4) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Leafeep tools

Write · Medium bulk_create_review_questions This tool creates new quiz review questions in bulk, modifying the review pool state. Write · Medium close_exam Closing an exam locks further submissions, which is a reversible state change (the exam could presumably be reopened). Write · Medium create_exam This tool creates new exam data and associated artifacts (student links, QR codes) but does not execute code, run queries, delete data, or move money. Write · Medium grade_exam Grading a submission creates or modifies a grade record in the system.

4 of Leafeep's 11 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Leafeep

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

Rate limit write operations

{
  "bulk_create_review_questions": {
    "limits": [
      {
        "counter": "bulk_create_review_questions_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_results": {
    "limits": [
      {
        "counter": "get_results_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 Leafeep — 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 LEAFEEP →

Instant setup, no code required.

FULL CATALOGUE

All 11 Leafeep tools

WRITE 4 tools

Write bulk_create_review_questions Bulk create OX review questions for the review pool. Each question needs a statement, correctAnswer (true/fals Write close_exam Close an exam (lock submissions). Write create_exam Create a question set and generate a student link + QR code. Write grade_exam Grade student submissions. Use answerId from get_results.

READ 7 tools

Read get_results Get full exam data: submissions, answers, grading, and statistics. Read get_review_pool_stats Get statistics about the review question pool coverage. Read get_student_history Get a student Read list_exams List all your question sets. Read list_students List all students with scores. Read setup Get the login link for Leafeep. After logging in, copy the token shown on the page and use the Read verify Paste the token from the login page to connect your account. Usage: verify <token>

FAQ

Questions about Leafeep

How do I prevent bulk modifications through Leafeep? +

The Leafeep server has 4 write tools including bulk_create_review_questions, close_exam, create_exam. 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 Leafeep.

How many tools does the Leafeep MCP server expose? +

11 tools across 2 categories: Read, Write. 7 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on Leafeep? +

Register the Leafeep 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 Leafeep tool call.

Deterministic rules across all 11 Leafeep tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LEAFEEP →

Instant setup, no code required.

11 Leafeep tools catalogued and risk-classified — across an index of 43,000+ MCP servers.