# brick_search_parts

Search or browse the full LDraw parts library. Without arguments, returns all categories with part counts. Use

Agent View of the PolicyLayer registry record for `brick_search_parts`. HTML page: https://policylayer.com/tools/dend-brick-mcp-app/brick-search-parts

## Facts

- Tool: `brick_search_parts`
- Server: Brick Builder MCP App (`dend/brick-mcp-app`) — https://policylayer.com/tools/dend-brick-mcp-app.md
- Homepage: https://github.com/dend/brick-mcp-app
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "brick_search_parts",
    "arguments": {}
  }
}
```

## Why brick_search_parts is rated Low

This tool retrieves information from a static parts library and returns catalog data. It performs no mutations, deletions, code execution, or financial operations. Searching and browsing are read-only operations with no destructive or side-effect capabilities. The blast radius if misused is minimal—an AI agent could retrieve catalog data but cannot modify scenes, delete content, or trigger external operations.

From the tool's own definition: "Tool name 'brick_search_parts' and description 'Search or browse the full LDraw parts library' indicate querying/browsing a catalog."

## Use case

AI agents call brick_search_parts to retrieve information from Brick Builder MCP App without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Brick Builder MCP App:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "brick_search_parts": {}
  }
}
```

## Other tools on Brick Builder MCP App (8)

- `brick_clear_scene` — Destructive — https://policylayer.com/tools/dend-brick-mcp-app/brick-clear-scene.md
- `brick_remove_brick` — Destructive — https://policylayer.com/tools/dend-brick-mcp-app/brick-remove-brick.md
- `brick_export_scene` — Read — https://policylayer.com/tools/dend-brick-mcp-app/brick-export-scene.md
- `brick_get_available` — Read — https://policylayer.com/tools/dend-brick-mcp-app/brick-get-available.md
- `brick_get_scene` — Read — https://policylayer.com/tools/dend-brick-mcp-app/brick-get-scene.md
- `brick_read_me` — Read — https://policylayer.com/tools/dend-brick-mcp-app/brick-read-me.md
- `brick_place` — Write — https://policylayer.com/tools/dend-brick-mcp-app/brick-place.md
- `brick_set_build_mode` — Write — https://policylayer.com/tools/dend-brick-mcp-app/brick-set-build-mode.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=dend-brick-mcp-app · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/dend-brick-mcp-app