resource_save
Load a resource and (re-)save it, optionally to a new path and with ResourceSaver flags. DESTRUCTIVE (writes a file) — gated by confirmation. Shares subresources by reference; use resource_duplicate for an independent copy.
This record as markdown: /tools/breakpoint-mcp/resource-save.md
What resource_save does on Breakpoint
AI agents use resource_save 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 |
|---|---|---|---|
flags | integer | — | ResourceSaver.SaverFlags bitmask (e.g. 32 = FLAG_COMPRESS) |
confirm | boolean | — | Skip the confirmation prompt (auto-approve) |
to_path | string | — | Destination res:// path (default: overwrite from_path) |
from_path | string | Yes | Source resource res:// path |
overwrite | boolean | — | Replace if it exists |
Parameters from the server's own tool schema.
Why resource_save is rated Medium
Although the tool modifies files on disk and is labeled 'DESTRUCTIVE' in the description, the core operation is writing/saving data reversibly. File writes are not inherently irreversible in the way DELETE or DROP operations are—saved files can be restored from backups, version control, or overwritten again. The confirmation gate further mitigates risk.
From the tool's definition Tool description explicitly states it 'saves' a resource 'optionally to a new path' with ResourceSaver flags.
Attacks that exploit this kind of access
The rule that runs resource_save 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_save, this is the rule to start with:
resource_save 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_save call is checked against it from then on.
Questions about resource_save
Load a resource and (re-)save it, optionally to a new path and with ResourceSaver flags. DESTRUCTIVE (writes a file) — gated by confirmation. Shares subresources by reference; use resource_duplicate for an independent copy. 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_save accepts 5 parameters: flags, confirm, to_path, from_path, overwrite. Required: from_path. 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_save: 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_save 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_save 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_save. 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_save 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