new_branch
Create a new branch with this name in the worktree (optional) (string, optional)
This record as markdown: /tools/io-github-aifity-omnigit-mcp/new-branch.md
What new_branch does on GitHub
AI agents use new_branch to create or update resources in GitHub, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitHub environment.
Why new_branch is rated Medium
Creating a branch is a write operation that adds a new ref to the repository. It is reversible (branches can be deleted) and does not execute code or destroy data. Medium severity because an AI agent could create many spurious branches or create branches from unintended commits, but the blast radius is limited.
From the tool's definition 'Create a new branch' — creates a new git branch, which is a reversible write operation
Attacks that exploit this kind of access
The rule that runs new_branch safely
PolicyLayer is an MCP gateway: it sits between your AI agents and GitHub, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For new_branch, this is the rule to start with:
new_branch stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect GitHub, apply this rule, and every new_branch call is checked against it from then on.
Questions about new_branch
Create a new branch with this name in the worktree (optional) (string, optional). It is categorised as a Write tool in the GitHub MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitHub MCP server in PolicyLayer and add a rule for new_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. Nothing to install.
new_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 new_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 new_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.
new_branch is provided by the GitHub MCP server (oci:ghcr.io/aifity/omnigit-mcp:0.5.0). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on GitHub, and thousands of servers like it.
This server
Across the catalogue