compose-build · Github MCP: Risk & Policy

WHAT IT DOES

What compose-build does on Github

AI agents invoke compose-build to trigger actions in Github. 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 compose-build needs a policy

The tool triggers Docker Compose build operations, which execute arbitrary build commands, potentially running scripts embedded in Dockerfiles. While not directly destructive (images can be cleaned up), it executes external operations whose effects depend on configuration arguments, fitting the Execute category.

From the tool's definition Tool performs 'Builds Docker Compose service images' — this executes Docker build processes with external side effects that depend on the compose configuration and Dockerfile arguments provided.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

compose-build Rate-limited

compose-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": {
    "compose-build": {
      "limits": [
        {
          "counter": "compose-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 Github, so you can run agents against it safely.

FAQ

Questions about compose-build

What does the compose-build tool do? +

Builds Docker Compose service images and returns structured per-service build status. It is categorised as a Execute tool in the Github MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on compose-build? +

Register the Github MCP server in PolicyLayer and add a rule for compose-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 Github. Nothing to install.

What risk level is compose-build? +

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

Can I rate-limit compose-build? +

Yes. Add a rate_limit block to the compose-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 compose-build completely? +

Set action: deny in the PolicyLayer policy for compose-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 compose-build? +

compose-build is provided by the Github MCP server (@paretools/github). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.