Resets the current HEAD to a specified state. Supports soft, mixed, hard, merge, and keep modes. The
AI agents call reset to permanently remove resources in Github — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
While soft and mixed resets are reversible, the tool explicitly supports hard reset mode which irreversibly discards working directory changes. Hard resets cannot be undone without access to the reflog, and in automated contexts or with subsequent operations, data loss becomes permanent. This makes it destructive rather than execute-only.
From the tool's definition Tool performs git reset operations with hard mode capability, which irreversibly discards uncommitted changes and moves HEAD to a specified state.
Documented attack patterns abuse exactly the kind of access reset gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Github, and nothing reaches the server without passing your rules. This is the rule we recommend for reset:
{
"version": "1",
"default": "deny",
"hide": [
"reset"
]
} reset disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Resets the current HEAD to a specified state. Supports soft, mixed, hard, merge, and keep modes. The. It is categorised as a Destructive tool in the Github MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Github MCP server in PolicyLayer and add a rule for reset: 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 Github. Nothing to install.
reset 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 reset 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 reset. 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.
reset is provided by the Github MCP server (@paretools/github). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Github, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
202 Github tools catalogued and risk-classified — across an index of 43,000+ MCP servers.