Delete a specific build
AI agents call jenkins_delete_build to permanently remove resources in Mcp Jenkins — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a build is a destructive operation that cannot be undone. Once a build is deleted, historical records, artifacts, and logs are lost permanently. This falls clearly into the Destructive category (ranked above Execute and Write) due to its irreversible nature. The high severity reflects that deleting builds can impact CI/CD pipelines, audit trails, and artifact management.
From the tool's definition Tool name is 'jenkins_delete_build' and description states 'Delete a specific build'. The verb 'delete' combined with the action of removing a build artifact is irreversible.
Attacks that exploit this kind of access
Delete a specific build. It is categorised as a Destructive tool in the Mcp Jenkins MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Jenkins MCP server in PolicyLayer and add a rule for jenkins_delete_build: 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 Jenkins. Nothing to install.
jenkins_delete_build 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 jenkins_delete_build 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 jenkins_delete_build. 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.
jenkins_delete_build is provided by the Mcp Jenkins MCP server (@kud/mcp-jenkins). 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 →