// SCAN REPORT

Brick Builder MCP App

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

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

Last updated: 1 Aug 2026

4 can modify or destroy data

5 read-only

9 tools total

Community server · catalogue entry checked 01/08/2026

How to control Brick Builder MCP App ↓

TOOL MAP

What Brick Builder MCP App exposes to your agents

Read (5) Write / Execute (2) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Brick Builder MCP App tools

Destructive · High brick_clear_scene This tool meets the Destructive category definition: it irreversibly deletes data (all scene bricks) in a single operation that cannot be undone. Destructive · Medium brick_remove_brick This tool irreversibly removes a brick and potentially cascades to remove additional bricks that lose structural support. Write · Medium brick_place This tool writes new brick data into the scene state. Write · Low brick_set_build_mode This is a Write operation because it creates or modifies data reversibly.

4 of Brick Builder MCP App'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 Brick Builder MCP App

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

Deny destructive operations

{
  "brick_clear_scene": {
    "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

{
  "brick_place": {
    "limits": [
      {
        "counter": "brick_place_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "brick_export_scene": {
    "limits": [
      {
        "counter": "brick_export_scene_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 Brick Builder MCP App — 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 BRICK BUILDER MCP APP →

Instant setup, no code required.

FULL CATALOGUE

All 9 Brick Builder MCP App tools

DESTRUCTIVE 2 tools

Destructive brick_clear_scene Remove all bricks from the scene. Destructive brick_remove_brick Remove a single brick by its ID. Use brick_get_scene to find brick IDs. Also removes any bricks that lose supp

WRITE 2 tools

Write brick_place Place one or more bricks. Input is CSV — one brick per line, columns: typeId,x,y,z,rotation,color. Rows are au Write brick_set_build_mode Set the build mode and/or snap flag.

READ 5 tools

Read brick_export_scene Export the scene as JSON or a summary. Read brick_get_available Returns popular brick types with their IDs and dimensions. You can also use any LDraw part number not listed h Read brick_get_scene Returns the current scene state with all placed bricks and their footprints. Call this ONCE at the start of a Read brick_read_me Returns the building guide, coordinate system, and examples. Call this BEFORE using any other brick tool for t Read brick_search_parts Search or browse the full LDraw parts library. Without arguments, returns all categories with part counts. Use

EXPLORE

Related servers

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

FAQ

Questions about Brick Builder MCP App

Can an AI agent delete data through the Brick Builder MCP App MCP server? +

Yes. The Brick Builder MCP App server exposes 2 destructive tools including brick_clear_scene, brick_remove_brick. 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 Brick Builder MCP App? +

The Brick Builder MCP App server has 2 write tools including brick_place, brick_set_build_mode. 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 Brick Builder MCP App.

How many tools does the Brick Builder MCP App MCP server expose? +

9 tools across 3 categories: Destructive, Read, Write. 5 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on Brick Builder MCP App? +

Register the Brick Builder MCP App 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 Brick Builder MCP App tool call.

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

ENFORCE POLICY ON BRICK BUILDER MCP APP →

Instant setup, no code required.

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

// WHERE THIS COMES FROM

These policies come from Brick Builder MCP App'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 →