AI agents use branch_protect to create or update resources in Git Steer — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Git Steer environment.
Applying branch protection rules modifies repository settings by enforcing or changing access controls, merge requirements, and push restrictions. This is a Write operation (creates/modifies configuration reversibly), but carries high severity because misconfiguring protection rules could expose critical branches to unauthorized pushes, force-pushes, or bypass of required reviews, potentially compromising repository…
From the tool's definition Apply branch protection rules
Attacks that exploit this kind of access
Apply branch protection rules. It is categorised as a Write tool in the Git Steer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Git Steer MCP server in PolicyLayer and add a rule for branch_protect: 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.
branch_protect is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the branch_protect 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 branch_protect. 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.
branch_protect 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 →