// SCAN REPORT

MCP Server Learning

33 tools. 10 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 4 Jul 2026

10 can modify or destroy data

23 read-only

33 tools total

Community server · catalogue entry verified 04/07/2026

How to control MCP Server Learning ↓

TOOL MAP

What MCP Server Learning exposes to your agents

Read (23) Write / Execute (9) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous MCP Server Learning tools

Destructive · High delete_notes Delete operations are classified as Destructive because they cannot be undone and result in permanent loss of data. Execute · Medium verify_derivative The tool likely computes or verifies mathematical derivatives, which involves executing a calculation or verification process. Execute · Medium verify_integral Based on the server description referencing mathematical expression verification and LaTeX support, 'verify_integral' likely executes a computation or verification process on a mathematical integral expression. Write · Low add_item_to_collection The tool name suggests adding an item to a collection, which is a reversible write operation that creates or modifies a collection's contents.

10 of MCP Server Learning's 33 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCP Server Learning

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

Deny destructive operations

{
  "delete_notes": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_item_to_collection": {
    "limits": [
      {
        "counter": "add_item_to_collection_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "check_connection": {
    "limits": [
      {
        "counter": "check_connection_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 MCP Server Learning — 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 MCP SERVER LEARNING →

Instant setup, no code required.

FULL CATALOGUE

All 33 MCP Server Learning tools

DESTRUCTIVE 1 tools

Destructive delete_notes delete_notes

EXECUTE 2 tools

Execute verify_derivative verify_derivative Execute verify_integral verify_integral

WRITE 7 tools

Write add_item_to_collection add_item_to_collection Write create_cards create_cards Write create_item create_item Write create_item_note create_item_note Write move_to_deck move_to_deck Write update_note update_note Write upload_cards upload_cards

READ 23 tools

Read check_connection check_connection Read check_identity check_identity Read extract_note_blocks extract_note_blocks Read extract_note_headers extract_note_headers Read get_backlinks get_backlinks Read get_collection_items get_collection_items Read get_flashcard_content get_flashcard_content Read get_item get_item Read get_item_notes get_item_notes Read get_item_templates Get templates showing all available Zotero item types and their fields. Read get_note get_note Read get_note_links get_note_links Read get_notes_by_tag get_notes_by_tag Read get_orphaned_notes Find notes that have no incoming or outgoing [[wikilinks]]. These may Read get_vault_stats Get statistics about the Obsidian vault: total note count, all tags, Read list_collections List all collections (folders) in the Zotero library. Use collection keys Read list_notes list_notes Read search_items search_items Read search_notes search_notes Read simplify_expression Simplify a mathematical expression and optionally show steps. Read sync sync Read verify_equivalence Verify if two mathematical expressions are equivalent. Read verify_proof verify_proof

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about MCP Server Learning

Can an AI agent delete data through the MCP Server Learning MCP server? +

Yes. The MCP Server Learning server exposes 1 destructive tools including delete_notes. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through MCP Server Learning? +

The MCP Server Learning server has 7 write tools including add_item_to_collection, create_cards, create_item. 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 MCP Server Learning.

How many tools does the MCP Server Learning MCP server expose? +

33 tools across 3 categories: Destructive, Read, Write. 23 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on MCP Server Learning? +

Register the MCP Server Learning 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 MCP Server Learning tool call.

Deterministic rules across all 33 MCP Server Learning tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP SERVER LEARNING →

Instant setup, no code required.

33 MCP Server Learning tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// WHERE THIS COMES FROM

These policies come from MCP Server Learning'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 →