Restart one build in Drone.
AI agents invoke drone_restart_build to trigger actions in Drone CI MCP Server. 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.
This tool executes an action that triggers an external CI/CD operation. While not destructive (the build can be restarted again), it goes beyond read/write of static data—it actively manipulates running pipeline state and can have cascading effects on dependent stages, deployments, or notifications.
From the tool's definition Tool name 'drone_restart_build' and description 'Restart one build in Drone' indicate triggering an external operation (restarting a CI/CD pipeline build) whose effects depend on arguments (which build to restart).
Attacks that exploit this kind of access
Restart one build in Drone. It is categorised as a Execute tool in the Drone CI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Drone CI MCP Server MCP server in PolicyLayer and add a rule for drone_restart_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 Drone CI MCP Server. Nothing to install.
drone_restart_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 drone_restart_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 drone_restart_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.
drone_restart_build is provided by the Drone CI MCP Server MCP server (leuzeus/mcp-drone-ci). 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 →