// SCAN REPORT

Loenn

82 tools. 34 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

34 can modify or destroy data

48 read-only

82 tools total

Community server · catalogue entry verified 03/07/2026

How to control Loenn ↓

TOOL MAP

What Loenn exposes to your agents

Read (48) Write / Execute (29) Destructive / Financial (5)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Loenn tools

Destructive · High remove_decal Removing a decal from a map file by index is a destructive operation; once removed, the decal and its configuration are gone and cannot be recovered without a prior backup. Destructive · High remove_entity The tool permanently removes a named entity from a Celeste map room. Destructive · High remove_room Removing a room from a Celeste map file is an irreversible deletion that cannot be undone through normal tool operations (there is no 'restore_room' or 'undo' capability). Destructive · High remove_styleground The tool removes styleground elements from a .bin map file.

34 of Loenn's 82 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Loenn

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

Deny destructive operations

{
  "remove_decal": {
    "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_decal": {
    "limits": [
      {
        "counter": "add_decal_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "ai_analyze_map": {
    "limits": [
      {
        "counter": "ai_analyze_map_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 Loenn — 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 LOENN →

Instant setup, no code required.

FULL CATALOGUE

All 82 Loenn tools

DESTRUCTIVE 5 tools

Destructive remove_decal Remove a decal by index. Destructive remove_entity Remove an entity from a room by its ID. Destructive remove_room Remove a room from a map. Destructive remove_styleground Remove a styleground from a map by its index in the layer. Destructive remove_trigger Remove a trigger from a room by its ID.

EXECUTE 5 tools

Execute build_pattern_library build_pattern_library Execute generate_terrain_map generate_terrain_map Execute install_loenn_manager install_loenn_manager Execute pcg_pipeline pcg_pipeline Execute pcg_skeleton_generate pcg_skeleton_generate

WRITE 24 tools

Write add_decal add_decal Write add_entity add_entity Write add_room add_room Write add_styleground add_styleground Write add_trigger add_trigger Write batch_add_entities batch_add_entities Write clone_room clone_room Write create_map Create a new empty Celeste .bin map file. Write generate_map_from_image generate_map_from_image Write generate_room_from_pattern generate_room_from_pattern Write import_room_json import_room_json Write move_entity Move an entity to a new position. Write move_room Move a room to a new world-space position. Write pcg_markov_fill pcg_markov_fill Write rename_room Rename a room in a map. Write resize_room Resize a room (snaps to 8-pixel grid, preserves tile data). Write set_map_dependencies set_map_dependencies Write set_map_metadata set_map_metadata Write set_room_tiles Set tile data for a room. Each row is a line of characters ('0'=air). Write update_entity update_entity Write update_room update_room Write update_room_settings update_room_settings Write update_styleground update_styleground Write wiki_save wiki_save

READ 48 tools

Read ai_analyze_map ai_analyze_map Read ai_describe_room ai_describe_room Read ai_suggest_entities ai_suggest_entities Read analyze_difficulty Estimate room or map difficulty from hazard density, nav aids, and tile coverage. Read analyze_entity_usage Analyze entity usage across the entire map. Read analyze_map Get detailed statistics about a map file. Read analyze_map_assets analyze_map_assets Read analyze_room_connectivity Analyze room adjacency graph showing isolated rooms, dead ends, and hubs. Read batch_validate_and_fix batch_validate_and_fix Read compare_maps Compare two maps and show structural differences. Read compare_rooms Compare two rooms in the same map side-by-side. Read detect_map_patterns Detect gameplay design archetypes (linear, hub, collectible-rich, etc.). Read export_room_json Export a room as a JSON file for external editing or sharing. Read find_entity_references Find all occurrences of an entity type across the map. Read get_effect_definition Read the source of a Lönn effect definition .lua file. Read get_entity_definition Read a Lönn entity Lua definition and extract its properties. Read get_loenn_manager_source Return the source code of the Lönn MCP Manager plugin. Read get_map_dependencies Read the mod dependencies list from a map's everest.yaml or meta node. Read get_map_metadata Read the map-level metadata block (Everest/celeste.yaml meta settings). Read get_mod_info Get information about the current mod project. Read get_room_settings get_room_settings Read get_room_tiles Get the complete tile grid for a room as text. Read get_trigger_definition Read the source of a Lönn trigger definition .lua file. Read ingest_external_map ingest_external_map Read list_decals List all decals in a room (foreground or background). Read list_effect_definitions List available Lönn effect definitions. Read list_entity_definitions List available Lönn entity definitions from the project. Read list_maps List all .bin map files in the project. Read list_stylegrounds list_stylegrounds Read list_trigger_definitions List available Lönn trigger definitions. Read pcg_mdmc_presets List all available MdMC configuration matrix presets. Read pcg_score_room pcg_score_room Read preview_map_section preview_map_section Read preview_terrain_biomes preview_terrain_biomes Read read_map_metadata Read high-level metadata from a map without listing all room contents. Read read_map_overview Parse a .bin map file and return a summary of rooms and structure. Read read_room Get detailed data for a specific room: tiles, entities, triggers. Read render_map_html render_map_html Read search_entities search_entities Read search_triggers Search for triggers across all rooms by type. Read suggest_improvements Suggest improvements for a room based on analysis. Read summarize_map_diff summarize_map_diff Read validate_map validate_map Read validate_room validate_room Read visualize_map_layout Generate an ASCII visualization of all room positions in a map. Read wiki_get Retrieve a specific wiki entry by key. Read wiki_list List all entries in the wiki cache. Read wiki_search Search the wiki cache by key, content, or tags.

EXPLORE

Related servers

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

FAQ

Questions about Loenn

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

Yes. The Loenn server exposes 5 destructive tools including remove_decal, remove_entity, remove_room. 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 Loenn? +

The Loenn server has 24 write tools including add_decal, add_entity, add_room. 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 Loenn.

How many tools does the Loenn MCP server expose? +

82 tools across 4 categories: Destructive, Execute, Read, Write. 48 are read-only. 34 can modify, create, or delete data.

How do I enforce a policy on Loenn? +

Register the Loenn 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 Loenn tool call.

Deterministic rules across all 82 Loenn tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LOENN →

Instant setup, no code required.

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