Restore a previously captured checkpoint. Plugin wraps the restore in a single ChangeHistory waypoint, so a single Ctrl+Z still works as an undo escape hatch. Args: - checkpointId (string)
AI agents use revert_to_checkpoint to create or update resources in Melo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Melo environment.
This tool restores a prior checkpoint state, which overwrites the current state of the Roblox Studio scene. While it is potentially destructive (overwriting current work), it is explicitly noted as reversible via a single Ctrl+Z undo, making it a Write-level operation rather than Destructive. However, the blast radius is high because it can overwrite large amounts of work across the entire scene if misused.
From the tool's definition Restore a previously captured checkpoint. Plugin wraps the restore in a single ChangeHistory waypoint, so a single Ctrl+Z still works as an undo escape hatch.
Attacks that exploit this kind of access
Restore a previously captured checkpoint. Plugin wraps the restore in a single ChangeHistory waypoint, so a single Ctrl+Z still works as an undo escape hatch. Args: - checkpointId (string). It is categorised as a Write tool in the Melo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Melo MCP server in PolicyLayer and add a rule for revert_to_checkpoint: 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 Melo. Nothing to install.
revert_to_checkpoint 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 revert_to_checkpoint 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 revert_to_checkpoint. 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.
revert_to_checkpoint is provided by the Melo MCP server (yannyhl/linkedsword-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →