vcs_stash
Manage stashes: op='push' saves and reverts your working changes (optional message); 'pop' re-applies the latest stash; 'list' returns the stash entries; 'drop' deletes a stash entry. 'push' and 'drop' are destructive and elicitation-gated (confirm:true bypasses) — push reverts every uncommitted ...
This record as markdown: /tools/breakpoint-mcp/vcs-stash.md
What vcs_stash does on Breakpoint
AI agents call vcs_stash 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 |
|---|---|---|---|
op | string | Yes | Stash operation |
ref | string | — | Stash ref for op='drop'/'pop', e.g. stash@{1} (default latest) |
confirm | boolean | — | Skip the confirmation prompt (op='push' / op='drop') |
message | string | — | Message for op='push' |
Parameters from the server's own tool schema.
Why vcs_stash is rated Critical
An AI agent that decides to call vcs_stash doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Breakpoint is gone. There is no undo for destructive operations.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs vcs_stash 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_stash, this is the rule to start with:
vcs_stash 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_stash call is checked against it from then on.
Questions about vcs_stash
Manage stashes: op='push' saves and reverts your working changes (optional message); 'pop' re-applies the latest stash; 'list' returns the stash entries; 'drop' deletes a stash entry. 'push' and 'drop' are destructive and elicitation-gated (confirm:true bypasses) — push reverts every uncommitted change in the working tree, and drop deletes an entry unrecoverably; pop and list are not gated. op='push' ERRORS when nothing was stashed (no tracked file has uncommitted changes) rather than reporting success — a success there would tell you work is parked when it is not. Untracked files are never stashed. 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_stash accepts 4 parameters: op, ref, confirm, message. Required: op. 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_stash: 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_stash 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_stash 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_stash. 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_stash 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