resource_create
Instantiate a Resource subclass and save it as a new file. DESTRUCTIVE (writes a file) — gated by confirmation. Optional initial properties use the tagged-Variant convention.
This record as markdown: /tools/breakpoint-mcp/resource-create.md
What resource_create does on Breakpoint
AI agents use resource_create 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 |
|---|---|---|---|
confirm | boolean | — | Auto-approve this destructive action (skip the confirmation prompt) |
to_path | string | Yes | Destination res:// path, e.g. res://styles/panel.tres |
class_name | string | Yes | Resource subclass to instantiate, e.g. StyleBoxFlat, Theme, GDScript |
properties | object | — | Initial property values (JSON scalars or __type__-tagged Variants) |
Parameters from the server's own tool schema.
Why resource_create is rated Medium
Although the description mentions 'DESTRUCTIVE', the action is file creation with confirmation gates, which is a Write operation—it creates new data reversibly. The file could be deleted or modified afterward. The 'gated by confirmation' qualifier significantly reduces the severity from the destructive category.
From the tool's definition Tool description explicitly states 'writes a file' and instantiates a Resource subclass, creating new persistent data.
Attacks that exploit this kind of access
The rule that runs resource_create 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 resource_create, this is the rule to start with:
resource_create 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Breakpoint, apply this rule, and every resource_create call is checked against it from then on.
Questions about resource_create
Instantiate a Resource subclass and save it as a new file. DESTRUCTIVE (writes a file) — gated by confirmation. Optional initial properties use the tagged-Variant convention. 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.
resource_create accepts 4 parameters: confirm, to_path, class_name, properties. Required: to_path, class_name. The full parameter table on this page comes from the server's own tool schema.
Register the Breakpoint MCP server in PolicyLayer and add a rule for resource_create: 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.
resource_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the resource_create 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.
Set action: deny in the PolicyLayer policy for resource_create. 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.
resource_create 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.
More on Breakpoint, and thousands of servers like it.
This server
Across the catalogue