collisionshape_add

SERVERBreakpoint SOURCEbreakpoint-mcp

Medium RISK CLASS

Category Write

Parameters 82 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/breakpoint-mcp/collisionshape-add.md

WHAT IT DOES

What collisionshape_add does on Breakpoint

AI agents use collisionshape_add to create or update resources in Breakpoint, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Breakpoint environment.

Parameter	Type	Required	Description
`dim`	string	—	Dimension: "2d" (default) or "3d"
`name`	string	—	Node name (default "CollisionShape2D"/"CollisionShape3D") A taken name gets a number appended (`SFX`->`SFX2`), reported as `coerced` + `requested`.
`size`	array	—	rect: [w, h] (2D) or [w, h, d] (3D)
`shape`	string	Yes	Shape kind: rect \| circle \| capsule \| polygon
`height`	number	—	capsule height
`points`	array	—	polygon: convex-hull points, [[x, y], …] (2D, ≥3) or [[x, y, z], …] (3D, ≥4)
`radius`	number	—	circle/capsule radius
`parent_path`	string	Yes	Parent node path (usually a body) relative to the scene root; "." for the root

Parameters from the server's own tool schema.

RISK

Why collisionshape_add is rated Medium

This tool creates and inserts new nodes into a Godot scene, which is a reversible write operation. Although it modifies scene structure, the explicit 'undoable' guarantee and lack of permanent deletion distinguish it from Destructive. It does not execute arbitrary code or trigger external operations (Execute), nor does it move data irreversibly.

From the tool's definition Tool description states it will 'Add a CollisionShape2D/3D node' and explicitly notes it is 'undoable', indicating reversible modification of scene data. The description emphasizes it modifies 'the edited scene' by adding nodes and shape resources.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs collisionshape_add safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Breakpoint, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For collisionshape_add, this is the rule to start with:

collisionshape_add Rate-limited

collisionshape_add stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "collisionshape_add": {
      "limits": [
        {
          "counter": "collisionshape_add_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Breakpoint, apply this rule, and every collisionshape_add call is checked against it from then on.

FAQ

Questions about collisionshape_add

What does the collisionshape_add tool do? +

Add a CollisionShape2D/3D node carrying a shape resource under a parent (usually a body) in the edited scene (undoable). shape is rect | circle | capsule | polygon; dim selects 2D (Rectangle/Circle/Capsule/ConvexPolygon 2D) or 3D (Box/Sphere/Capsule/ConvexPolygon 3D). In-scene and undoable — not gated. It is categorised as a Write tool in the Breakpoint MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does collisionshape_add accept? +

collisionshape_add accepts 8 parameters: dim, name, size, shape, height, points, radius, parent_path. Required: shape, parent_path. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on collisionshape_add? +

Register the Breakpoint MCP server in PolicyLayer and add a rule for collisionshape_add: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Breakpoint. Nothing to install.

What risk level is collisionshape_add? +

collisionshape_add is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit collisionshape_add? +

Yes. Add a rate_limit block to the collisionshape_add rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block collisionshape_add completely? +

Set action: deny in the PolicyLayer policy for collisionshape_add. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides collisionshape_add? +

collisionshape_add is provided by the Breakpoint MCP server (breakpoint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Breakpoint, and thousands of servers like it.

This server

All 280 Breakpoint tools →

Across the catalogue

add-tag on Kanban MCP Server →kb_add on Persistent Kb → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →