vcs_restore
Discard uncommitted working-tree changes to the given paths, restoring them from the index/HEAD (git restore -- <paths>). DESTRUCTIVE — the discarded edits are unrecoverable — so it is elicitation-gated: pass confirm:true to bypass the prompt on clients that can't elicit.
This record as markdown: /tools/breakpoint-mcp/vcs-restore.md
What vcs_restore does on Breakpoint
AI agents call vcs_restore to permanently remove resources in Breakpoint, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
paths | array | Yes | Paths to discard changes for (res:// or repo-relative) |
confirm | boolean | — | Skip the confirmation prompt |
Parameters from the server's own tool schema.
Why vcs_restore is rated Critical
The tool explicitly states it is destructive and that discarded edits are unrecoverable. It performs a `git restore` which permanently discards uncommitted working-tree changes with no way to recover them.
From the tool's definition DESTRUCTIVE — the discarded edits are unrecoverable — so it is elicitation-gated: pass confirm:true to bypass the prompt
Attacks that exploit this kind of access
The rule that runs vcs_restore 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 vcs_restore, this is the rule to start with:
vcs_restore is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Breakpoint, apply this rule, and every vcs_restore call is checked against it from then on.
Questions about vcs_restore
Discard uncommitted working-tree changes to the given paths, restoring them from the index/HEAD (git restore -- <paths>). DESTRUCTIVE — the discarded edits are unrecoverable — so it is elicitation-gated: pass confirm:true to bypass the prompt on clients that can't elicit. It is categorised as a Destructive tool in the Breakpoint MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
vcs_restore accepts 2 parameters: paths, confirm. Required: paths. 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 vcs_restore: 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.
vcs_restore 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 vcs_restore 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 vcs_restore. 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.
vcs_restore 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.
Across the catalogue