Discard unsaved changes in an open buffer and reload its on-disk contents.
AI agents call discard_buffer_changes to permanently remove resources in Vigentic MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly discards unsaved changes in a buffer. Any work that has not been saved to disk is permanently lost with no way to recover it, making this a destructive operation. The severity is high because an AI agent misusing this tool could cause permanent loss of in-progress work across files.
From the tool's definition Discard unsaved changes in an open buffer and reload its on-disk contents.
Attacks that exploit this kind of access
Discard unsaved changes in an open buffer and reload its on-disk contents. It is categorised as a Destructive tool in the Vigentic MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Vigentic MCP server in PolicyLayer and add a rule for discard_buffer_changes: 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 Vigentic MCP. Nothing to install.
discard_buffer_changes 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 discard_buffer_changes 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 discard_buffer_changes. 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.
discard_buffer_changes is provided by the Vigentic MCP server (munozu/vigentic-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 →