진행 중인 빌드를 취소합니다. (GitHub Actions run / GitLab pipeline)
AI agents call ci_cancel_build to permanently remove resources in Mimi Seed — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling a CI build is an irreversible action: once cancelled, the build run cannot be resumed. This is a destructive operation with a medium blast radius — it can interrupt deployments or release pipelines, but does not delete code or data.
From the tool's definition 진행 중인 빌드를 취소합니다 (Cancel an in-progress build — GitHub Actions run / GitLab pipeline)
Attacks that exploit this kind of access
진행 중인 빌드를 취소합니다. (GitHub Actions run / GitLab pipeline). It is categorised as a Destructive tool in the Mimi Seed MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mimi Seed MCP server in PolicyLayer and add a rule for ci_cancel_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 Mimi Seed. Nothing to install.
ci_cancel_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 ci_cancel_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 ci_cancel_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.
ci_cancel_build is provided by the Mimi Seed MCP server (@yoonion/mimi-seed-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
ci_cancel_build is one line of Mimi Seed's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →