AI agents call ci_list_recent_builds to retrieve information from Mimi Seed without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves historical build information without modifying, executing, or deleting any data. It is a read-only operation that returns metadata about CI builds. No destructive, financial, or executable actions are performed.
From the tool's definition Tool name 'ci_list_recent_builds' and description 'retrieves recent build list' with filtering by branch/workflow indicate a query/list operation with no side effects.
Attacks that exploit this kind of access
최근 빌드 목록을 조회합니다. 특정 브랜치나 워크플로로 필터링 가능. It is categorised as a Read tool in the Mimi Seed MCP Server, which means it retrieves data without modifying state.
Register the Mimi Seed MCP server in PolicyLayer and add a rule for ci_list_recent_builds: 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_list_recent_builds is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the ci_list_recent_builds 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_list_recent_builds. 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_list_recent_builds 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_list_recent_builds 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 →