Save, list, apply, pop, or drop stash entries.
AI agents call git_stash to permanently remove resources in Git — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool spans multiple operations: listing and applying/popping stashes are reversible (Read/Write), but 'drop' permanently deletes stash entries with no recovery path. Per the rules, the most severe applicable category applies. Severity is medium because stash entries are typically temporary saves and losing them, while unfortunate, usually doesn't destroy committed work.
From the tool's definition 'drop stash entries' — dropping a stash irreversibly deletes saved work; 'pop' also removes the stash entry after applying it
Attacks that exploit this kind of access
Save, list, apply, pop, or drop stash entries. It is categorised as a Destructive tool in the Git MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Git MCP server in PolicyLayer and add a rule for git_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 Git. Nothing to install.
git_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 git_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 git_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.
git_stash is provided by the Git MCP server (selfagency/git-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 →