Create a new branch in a GitLab repository.
AI agents use create_branch_tool to create or update resources in MCP Gitlab — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Gitlab environment.
Creating a branch is a reversible write operation that modifies repository state by adding a new branch reference. It does not execute code, trigger financial transactions, or irreversibly destroy data. While it affects the repository structure, the action can be undone by deleting the branch.
From the tool's definition Tool name 'create_branch_tool' and description 'Create a new branch in a GitLab repository' indicate creation of a new repository resource.
Attacks that exploit this kind of access
Create a new branch in a GitLab repository. It is categorised as a Write tool in the MCP Gitlab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Gitlab MCP server in PolicyLayer and add a rule for create_branch_tool: 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 MCP Gitlab. Nothing to install.
create_branch_tool 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_branch_tool 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_branch_tool. 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_branch_tool is provided by the MCP Gitlab MCP server (mcp-gitlab-crunchtools). 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 →