List, create, or delete tags. Supports GPG/SSH signed tags.
AI agents call git_tag to permanently remove resources in Git — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although git_tag also supports create and list operations (which would be Write/Read), the presence of the delete capability elevates this to Destructive. Deletion of Git tags cannot be easily undone if they have been pushed to shared repositories, and removing release tags could break build systems or documentation that depend on them.
From the tool's definition Tool description states 'delete tags' explicitly. Tags in Git are references that can be pushed to repositories and are often used to mark releases or important points in history.
Attacks that exploit this kind of access
List, create, or delete tags. Supports GPG/SSH signed tags. It is categorised as a Destructive tool in the Git MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Git MCP server in PolicyLayer and add a rule for git_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 Git. Nothing to install.
git_tag is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the git_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 git_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.
git_tag 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 →