cloudsave_scaffold
Generate save/load cloud-save helpers against an installed backend SDK. FEATURE-DETECTED both ways: if the SDK provides no cloud-save API (Photon is realtime transport), degrades to 'unsupported_feature'; if the SDK is not installed, degrades to 'install <SDK> first'. Neither writes anything. DES...
This record as markdown: /tools/breakpoint-mcp/cloudsave-scaffold.md
What cloudsave_scaffold does on Breakpoint
AI agents use cloudsave_scaffold 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 |
|---|---|---|---|
sdk | string | Yes | Which backend SDK to target |
confirm | boolean | — | Auto-approve this destructive action (skip the confirmation prompt) |
to_path | string | — | Destination res:// .gd path (default res://backend/cloud_save.gd) |
overwrite | boolean | — | Overwrite if the file already exists (default false) |
Parameters from the server's own tool schema.
Why cloudsave_scaffold is rated Medium
Although the description uses the word 'DESTRUCTIVE', the actual operation is file creation (writing a .gd GDScript file), which is reversible. This is a Write action, not Destructive, since the file can be deleted or overwritten by the user. The 'gated' qualifier suggests access controls are in place.
From the tool's definition Tool description explicitly states it 'writes a .gd' file. The phrase 'DESTRUCTIVE (writes a .gd) — gated' indicates file creation/modification.
Attacks that exploit this kind of access
The rule that runs cloudsave_scaffold 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 cloudsave_scaffold, this is the rule to start with:
cloudsave_scaffold 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 cloudsave_scaffold call is checked against it from then on.
Questions about cloudsave_scaffold
Generate save/load cloud-save helpers against an installed backend SDK. FEATURE-DETECTED both ways: if the SDK provides no cloud-save API (Photon is realtime transport), degrades to 'unsupported_feature'; if the SDK is not installed, degrades to 'install <SDK> first'. Neither writes anything. DESTRUCTIVE (writes a .gd) — 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.
cloudsave_scaffold accepts 4 parameters: sdk, confirm, to_path, overwrite. Required: sdk. 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 cloudsave_scaffold: 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.
cloudsave_scaffold 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 cloudsave_scaffold 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 cloudsave_scaffold. 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.
cloudsave_scaffold 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