AI agents call github_repo_status to retrieve information from Github without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only inspection of Git repository state and configuration. It queries local repository information (status, branches, remotes, upstream tracking) and MCP policy constraints, returning data without creating, modifying, deleting, or executing any operations.
From the tool's definition Tool name and description indicate it "Inspect[s] a local Git repository status, branch, remotes, upstream, and MCP allowed roots" — a query operation that retrieves repository metadata with no modifications or side effects.
Attacks that exploit this kind of access
Inspect a local Git repository status, branch, remotes, upstream, and MCP allowed roots. It is categorised as a Read tool in the Github MCP Server, which means it retrieves data without modifying state.
Register the Github MCP server in PolicyLayer and add a rule for github_repo_status: 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 Github. Nothing to install.
github_repo_status 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 github_repo_status 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 github_repo_status. 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.
github_repo_status is provided by the Github MCP server (matiasnjacob/github-mcp). 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 →