Przywróć kampanię z wcześniej zapisanego snapshotu.
AI agents use restore_campaign_snapshot to create or update resources in RPG Ledger MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your RPG Ledger MCP Server environment.
Restoring from a snapshot overwrites current campaign state with an earlier version. This is a Write operation (reversible in principle, since the snapshot exists), but it is high severity because it replaces all current campaign data — characters, inventory, quests, logs — potentially losing any unsaved progress since the last snapshot.
From the tool's definition 'restore_campaign_snapshot' - restores a campaign from a previously saved snapshot
Attacks that exploit this kind of access
Przywróć kampanię z wcześniej zapisanego snapshotu. It is categorised as a Write tool in the RPG Ledger MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the RPG Ledger MCP Server MCP server in PolicyLayer and add a rule for restore_campaign_snapshot: 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 RPG Ledger MCP Server. Nothing to install.
restore_campaign_snapshot 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 restore_campaign_snapshot 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 restore_campaign_snapshot. 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.
restore_campaign_snapshot is provided by the RPG Ledger MCP Server MCP server (sepa79/rpg-ledger-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 →