Revert local changes for a receive-only folder, matching remote state.
AI agents call revert_folder to permanently remove resources in Syncthing MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Reverting local changes is an irreversible destructive operation — any local modifications, additions, or files not present on the remote will be permanently overwritten or deleted to match the remote state. There is no indication of a recovery mechanism, making this a destructive action with high blast radius if misused on the wrong folder.
From the tool's definition Revert local changes for a receive-only folder, matching remote state
Attacks that exploit this kind of access
Revert local changes for a receive-only folder, matching remote state. It is categorised as a Destructive tool in the Syncthing MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Syncthing MCP Server MCP server in PolicyLayer and add a rule for revert_folder: 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 Syncthing MCP Server. Nothing to install.
revert_folder is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the revert_folder 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_folder. 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_folder is provided by the Syncthing MCP Server MCP server (zaphodsdad/syncthing-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 →