Get current Git branch.
AI agents call getCurrentBranch to retrieve information from GitHub MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves the current branch name from a repository—a read-only query with no side effects, no code execution, and no data modification. It poses minimal risk in the context of an AI agent using GitHub MCP tools, as it cannot alter repository state or trigger external operations.
From the tool's definition Tool name 'getCurrentBranch' and description 'Get current Git branch' indicate a query operation that retrieves branch information without modifying any data.
Attacks that exploit this kind of access
Get current Git branch. It is categorised as a Read tool in the GitHub MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GitHub MCP Server MCP server in PolicyLayer and add a rule for getCurrentBranch: 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 MCP Server. Nothing to install.
getCurrentBranch 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 getCurrentBranch 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 getCurrentBranch. 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.
getCurrentBranch is provided by the GitHub MCP Server MCP server (j-nowcow/github-mcp-practice). 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 →