ci_trigger_build · Mimi Seed MCP: Risk & Policy

WHAT IT DOES

What ci_trigger_build does on Mimi Seed

AI agents invoke ci_trigger_build to trigger actions in Mimi Seed. 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.

WHY IT NEEDS A POLICY

Why ci_trigger_build needs a policy

A CI trigger tool runs code and initiates automated build/deployment workflows—classic Execute category behavior. The blast radius is high because a malicious agent could trigger builds for arbitrary app versions, sign them with compromised credentials, or deploy to production stores without authorization.

From the tool's definition Tool name 'ci_trigger_build' indicates triggering a CI/CD pipeline build process. The sibling tools include 'android_generate_keystore', 'android_signing_setup', and 'appstore_attach_build', which establish this server's focus on mobile app build and…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ci_trigger_build Rate-limited

ci_trigger_build stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ci_trigger_build": {
      "limits": [
        {
          "counter": "ci_trigger_build_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Mimi Seed, so you can run agents against it safely.

FAQ

Questions about ci_trigger_build

What does the ci_trigger_build tool do? +

ci_trigger_build. It is categorised as a Execute tool in the Mimi Seed MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ci_trigger_build? +

Register the Mimi Seed MCP server in PolicyLayer and add a rule for ci_trigger_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.

What risk level is ci_trigger_build? +

ci_trigger_build is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit ci_trigger_build? +

Yes. Add a rate_limit block to the ci_trigger_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.

How do I block ci_trigger_build completely? +

Set action: deny in the PolicyLayer policy for ci_trigger_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.

What MCP server provides ci_trigger_build? +

ci_trigger_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.