Delete a tag from a repository.
AI agents call delete_tag to permanently remove resources in Bitbucket — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes version control metadata (a tag) from a repository. Tags are often used to mark releases, milestones, or stable versions. Deletion is irreversible and could break downstream processes, CI/CD pipelines, or release management workflows that depend on tag history. This is a classic destructive operation with no undo mechanism in normal workflows.
From the tool's definition Tool name is 'delete_tag' and description states 'Delete a tag from a repository.' The verb 'delete' is explicitly destructive—tags are typically immutable markers in version control systems, and deleting one cannot be undone without repository admin access…
Attacks that exploit this kind of access
Delete a tag from a repository. It is categorised as a Destructive tool in the Bitbucket MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Bitbucket MCP server in PolicyLayer and add a rule for delete_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 Bitbucket. Nothing to install.
delete_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 delete_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 delete_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.
delete_tag is provided by the Bitbucket MCP server (javimaligno/mcp-server-bitbucket). 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 →