Remove a repository from managed repos
AI agents call config_remove_repo to permanently remove resources in Git Steer — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a repository from management is an irreversible action that cannot be undone without manual intervention and reconfiguration. This matches the Destructive category definition of actions that cannot be undone. While not a data deletion per se, it eliminates the repository from the managed state, which is functionally destructive in the context of this autonomous management system.
From the tool's definition Tool description explicitly states 'Remove a repository from managed repos' — a destructive operation that irreversibly deletes or unmanages a repository configuration.
Attacks that exploit this kind of access
Remove a repository from managed repos. It is categorised as a Destructive tool in the Git Steer MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Git Steer MCP server in PolicyLayer and add a rule for config_remove_repo: 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 Steer. Nothing to install.
config_remove_repo 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 config_remove_repo 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 config_remove_repo. 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.
config_remove_repo is provided by the Git Steer MCP server (ry-ops/git-steer). 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 →