AI agents use fabric_git_create_branch 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.
Creating a branch is a reversible modification of repository state. It does not execute code, delete data, or move money. However, it has medium severity because an agent could create numerous branches to clutter a repository, create branches with misleading names for supply-chain attacks, or establish vectors for malicious workflows in a CI/CD context.
From the tool's definition Tool name contains 'create' and description states 'Create a new branch from an existing branch.' This is a write operation that modifies repository state by adding a new branch.
Attacks that exploit this kind of access
[git-fabric] Create a new branch from an existing branch. 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 fabric_git_create_branch: 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.
fabric_git_create_branch 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 fabric_git_create_branch 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 fabric_git_create_branch. 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.
fabric_git_create_branch 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 →