List git branches for a project
AI agents call git_branch_list to retrieve information from Coding MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only operation to enumerate git branches. It retrieves data about the repository state but has no side effects, does not execute code, and does not modify data. This is a straightforward information retrieval task, making it a Read category risk with low severity.
From the tool's definition Tool name is 'git_branch_list' and description states 'List git branches for a project' — this is a query operation that retrieves branch information without modifying or executing anything.
Attacks that exploit this kind of access
List git branches for a project. It is categorised as a Read tool in the Coding MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Coding MCP Server MCP server in PolicyLayer and add a rule for git_branch_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 Coding MCP Server. Nothing to install.
git_branch_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_branch_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_branch_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_branch_list is provided by the Coding MCP Server MCP server (kieutrongthien/coding-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 →