AI agents use git_create_branch to create or update resources in Git — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Git environment.
Creating a Git branch modifies repository state by adding a new reference, but this is reversible—branches can be deleted without data loss. This fits the Write category (creates or modifies data reversibly). Severity is medium because misuse could create confusion, pollute the branch namespace, or interfere with workflows, but the damage is easily undone.
From the tool's definition Tool explicitly creates a branch from current HEAD or an explicit ref. Creating a branch is a write operation that modifies the repository structure by adding a new ref, which is reversible through branch deletion.
Attacks that exploit this kind of access
Create a branch from current HEAD or an explicit ref. It is categorised as a Write tool in the Git MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Git MCP server in PolicyLayer and add a rule for git_create_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. Nothing to install.
git_create_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_create_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_create_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_create_branch is provided by the Git MCP server (selfagency/git-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 →