Ice Puzzle

63 tools. 42 can modify or destroy data without limits.

11 destructive tools with no built-in limits. Policy required.

Last updated:

42 can modify or destroy data
21 read-only
63 tools total

Community server · catalogue entry verified 30/06/2026

How to control Ice Puzzle ↓

What Ice Puzzle exposes to your agents

Read (21) Write / Execute (31) Destructive / Financial (11)
Critical Risk

The most dangerous Ice Puzzle tools

42 of Ice Puzzle's 63 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Ice Puzzle

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

Deny destructive operations
{
  "clear_level": {
    "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_pushable_rock": {
    "limits": [
      {
        "counter": "add_pushable_rock_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "analyze_difficulty": {
    "limits": [
      {
        "counter": "analyze_difficulty_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register Ice Puzzle — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON ICE PUZZLE →

Instant setup, no code required.

All 63 Ice Puzzle tools

WRITE 26 tools
Write add_pushable_rock Add pushable rocks Write add_thin_ice Add thin ice tiles (break after crossing) Write add_warp_pair Add a warp portal pair connecting two positions Write create_level Create a new empty ice puzzle level Write fill_region Fill a rectangular region with a tile type. Auto-solves. Write import_level Import a level from PuzzleData JSON Write move_tile Move one tile/special element from one coordinate to another. Auto-solves. Write place_tile Place a tile (rock, lava, hot_coals, or spike) at position. Auto-solves. Write place_tiles_batch Place multiple tiles at once. Auto-solves. Write preview_level Create or update a shareable preview link without publishing to marketplace Write publish_level Publish the current draft as a marketplace level Write redo Redo the most recently undone operation Write rename_level Rename the current working draft without recreating it Write restore_published_level Restore an unpublished marketplace level back to ACTIVE status Write revert_to_last_solvable Restore the latest known solvable state Write save_draft Save the current draft to Firebase (requires authentication) Write save_local_draft Save a snapshot of the current draft in local MCP memory Write seed_layout_pattern Apply a starter rock skeleton pattern to bootstrap solvable layout design Write set_barrier Set barrier position (kills if pressure plate not activated) Write set_goal Set the goal position (can be on edge/wall) Write set_grid_size Resize the level grid. Elements outside new bounds are removed. Write set_par Set explicit par (target shortest optimal move count) for the current draft Write set_par_to_shortest Solve and set par to the current solver shortest path length Write set_pressure_plate Set pressure plate position (deactivates barrier) Write set_start Set the player start position Write undo Undo the last edit operation
READ 21 tools
Read analyze_difficulty Analyze current level difficulty and characteristics Read auth_status Check Firebase authentication status Read check_publish_readiness Check publish blockers: auth status + strict quality gate Read export_level Export the current working draft as PuzzleData JSON Read get_campaign_example Get one campaign level example (by level number or ID) with solution and optional PuzzleData Read get_game_rules Get comprehensive ice puzzle game rules and design guide Read get_level Get the current working draft level with details and visualization Read get_level_requirements Get requirements for publishable levels Read get_my_published_level Get one of your published marketplace levels by ID Read get_tile_types Get all tile types with behavior descriptions Read interaction_faq Get quick-reference interaction outcomes for adjacent mechanic combinations Read list_campaign_examples List campaign level examples by difficulty tier (easy/medium/hard) with solver solutions Read list_drafts List all locally saved draft snapshots Read list_my_published_levels List your marketplace levels with status filter, sorting, and pagination Read list_remote_drafts List all remote drafts from Firebase Read load_draft Load a draft from Firebase by ID Read load_local_draft Load a locally saved draft snapshot by ID Read reachable_from Analyze all reachable landing positions from a starting coordinate Read suggest_skeleton_layout Suggest starter rock skeleton plans without modifying the current draft Read test_placement Dry-run placing one tile and solve without modifying the draft Read visualize_level Show ASCII art visualization of current level

Related servers

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

Questions about Ice Puzzle

Can an AI agent delete data through the Ice Puzzle MCP server? +

Yes. The Ice Puzzle server exposes 11 destructive tools including clear_level, clear_region, delete_draft. 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 Ice Puzzle? +

The Ice Puzzle server has 26 write tools including add_pushable_rock, add_thin_ice, add_warp_pair. 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 Ice Puzzle.

How many tools does the Ice Puzzle MCP server expose? +

63 tools across 4 categories: Destructive, Execute, Read, Write. 21 are read-only. 42 can modify, create, or delete data.

How do I enforce a policy on Ice Puzzle? +

Register the Ice Puzzle 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 Ice Puzzle tool call.

Deterministic rules across all 63 Ice Puzzle tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

63 Ice Puzzle tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.