Stop/abort a running build
AI agents invoke jenkins_stop_build to trigger actions in Mcp Jenkins. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes an action against Jenkins infrastructure by aborting an active build. While not destructive (the build isn't deleted, just halted), and not financial, it is an Execute action because it triggers a control operation on external systems. Severity is high because stopping a production build could interrupt CI/CD pipelines, deployments, or critical operations.
From the tool's definition Tool description states "Stop/abort a running build" - this triggers an external operation (stopping a build process) whose effects depend on which build is targeted.
Attacks that exploit this kind of access
Stop/abort a running build. It is categorised as a Execute tool in the Mcp Jenkins MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Jenkins MCP server in PolicyLayer and add a rule for jenkins_stop_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_stop_build is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the jenkins_stop_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_stop_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_stop_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 →