force
Force removal even if worktree is dirty or locked (optional, default: false) (boolean, optional)
This record as markdown: /tools/io-github-aifity-omnigit-mcp/force.md
What force does on GitHub
AI agents call force 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.
Why force is rated Critical
This tool forcibly removes a git worktree regardless of its state, potentially causing permanent loss of uncommitted work or locked resources. While the parameter itself is boolean and optional, the semantic meaning of 'force removal' combined with the GitHub server context (git operations) places this firmly in the Destructive category. The blast radius is high if misused—an agent could wipe local work.
From the tool's definition 'Force removal even if worktree is dirty or locked' indicates irreversible deletion of git worktree state without safety checks or reversibility constraints.
Attacks that exploit this kind of access
The rule that runs force safely
PolicyLayer is an MCP gateway: it sits between your AI agents and GitHub, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For force, this is the rule to start with:
force 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 GitHub, apply this rule, and every force call is checked against it from then on.
Questions about force
Force removal even if worktree is dirty or locked (optional, default: false) (boolean, optional). 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 force: 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.
force 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 force 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 force. 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.
force is provided by the GitHub MCP server (oci:ghcr.io/aifity/omnigit-mcp:0.5.0). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on GitHub, and thousands of servers like it.
Across the catalogue