Creates a new branch in the active local git repository.
AI agents use create_git_branch to create or update resources in Git PR MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Git PR MCP Server environment.
Creating a git branch is a reversible operation that modifies repository state by introducing a new ref. It does not execute arbitrary code, delete data, or involve financial transactions. While it's a modification, branches can be deleted, making this a Write rather than Destructive action.
From the tool's definition Tool description states it 'Creates a new branch in the active local git repository.' The verb 'creates' and the action of adding a new branch to the repository constitute data modification.
Attacks that exploit this kind of access
Creates a new branch in the active local git repository. It is categorised as a Write tool in the Git PR MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Git PR MCP Server MCP server in PolicyLayer and add a rule for create_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 Git PR MCP Server. Nothing to install.
create_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 create_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 create_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.
create_git_branch is provided by the Git PR MCP Server MCP server (peterj/git-pr-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 →