Create a new branch in a GitLab project
AI agents use create_branches to create or update resources in GitLab MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitLab MCP Server environment.
Creating a branch is a reversible write operation that modifies repository state by introducing a new reference. While it creates metadata/structure rather than file content, it is not reading data (Read), does not execute arbitrary code (Execute), is not irreversible (Destructive—branches can be deleted), and has no financial impact (Financial).
From the tool's definition Tool description: 'Create a new branch in a GitLab project'. The verb 'Create' and action of adding a new branch (a git ref) constitutes data creation that is reversible via delete_branches.
Attacks that exploit this kind of access
Create a new branch in a GitLab project. It is categorised as a Write tool in the GitLab MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitLab MCP Server MCP server in PolicyLayer and add a rule for create_branches: 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 GitLab MCP Server. Nothing to install.
create_branches 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_branches 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_branches. 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_branches is provided by the GitLab MCP Server MCP server (lucky-dersan/gitlab-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 →