list_branches
AI agents call list_branches 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.
The 'list' operation retrieves and enumerates existing branches in a repository without side effects, alter, or delete operations. This is a standard read-only API query with minimal risk of misuse by an AI agent. Severity is low because it only exposes repository structure information that is typically public or internal metadata.
From the tool's definition Tool name 'list_branches' with a 'list' verb indicates a retrieval operation that queries branch data without modification. The context of GitHub API tools and sibling tools like 'create_branch' further confirms that 'list_branches' performs a read-only query.
Attacks that exploit this kind of access
list_branches. 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 list_branches: 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.
list_branches 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 list_branches 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 list_branches. 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.
list_branches is provided by the GitHub MCP Server MCP server (software-engineer-mj/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 →