AI agents call git_steer_repo_list to retrieve information from Git Steer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about repositories without creating, modifying, deleting, or executing any operations. The blast radius of misuse is minimal—an attacker gains only visibility into which repositories exist and are accessible, not access to their contents, secrets, or ability to trigger actions. This is a standard enumeration capability with low security impact.
From the tool's definition Tool name and description indicate listing repositories: 'List GitHub repositories accessible to the token. Optionally filter by org.' The verb 'list' and lack of any modification or execution capability confirm this is a read-only operation.
Attacks that exploit this kind of access
List GitHub repositories accessible to the token. Optionally filter by org. It is categorised as a Read tool in the Git Steer MCP Server, which means it retrieves data without modifying state.
Register the Git Steer MCP server in PolicyLayer and add a rule for git_steer_repo_list: 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.
git_steer_repo_list is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the git_steer_repo_list 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 git_steer_repo_list. 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.
git_steer_repo_list 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 →