AI agents use repo_create 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 repository is a Write-category action because it creates new data structures reversibly. However, severity is high because unauthorized repository creation could be used to establish malicious codebases, pollute the organization's namespace, waste resources, or create confusion about the source of code.
From the tool's definition Tool name 'repo_create' and description 'Create a new repository' indicate data creation. This creates a new GitHub repository, which is a reversible write operation (the repository can be deleted later).
Attacks that exploit this kind of access
Create a new repository. 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 repo_create: 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.
repo_create 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 repo_create 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 repo_create. 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.
repo_create 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 →