Lists all branches or creates a new branch
AI agents use git-branch to create or update resources in GitHub MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitHub MCP Server environment.
The tool has dual functionality: listing branches (Read) and creating new branches (Write). Per the rules, the most severe applicable category wins. Creating a branch is a reversible write operation — branches can be deleted — so this is Write rather than Destructive.
From the tool's definition 'creates a new branch' — the tool can create a new branch in addition to listing branches
Attacks that exploit this kind of access
Lists all branches or creates a new branch. It is categorised as a Write tool in the GitHub MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitHub MCP Server MCP server in PolicyLayer and add a rule for git-branch: 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.
git-branch is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the git-branch 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. 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 is provided by the GitHub MCP Server MCP server (jungchihoon/github-mcp-server). 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 →