Create a tag at ref.
AI agents use create_tag to create or update resources in GitLab MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitLab MCP environment.
Creating a tag is a reversible write operation (tags can be deleted). It modifies repository metadata by introducing a new reference point, but does not execute arbitrary code, delete data, or move funds. While tags are often used to mark releases and can have downstream effects in CI/CD pipelines, the tool itself only creates the tag object.
From the tool's definition Tool name is 'create_tag' and description states 'Create a tag at `ref`.' This is a write operation that creates a new tag object in the repository.
Attacks that exploit this kind of access
Create a tag at ref. It is categorised as a Write tool in the GitLab MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitLab MCP server in PolicyLayer and add a rule for create_tag: 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. Nothing to install.
create_tag 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_tag 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_tag. 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_tag is provided by the GitLab MCP server (shahabmosavi/gitlab_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 →