AI agents invoke build to trigger actions in Android Project 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.
Building an Android project triggers compilation, resource processing, and potentially arbitrary build script execution. While not destructive in itself, it executes external build tools and code whose effects depend on the project contents. This qualifies as Execute rather than Write, because it runs a complex external operation (the build system) that can have side effects beyond simple data modification.
From the tool's definition Tool description: 'Build the Android project in the folder' — builds code, which compiles and links binaries. Build processes can execute arbitrary code (pre-build hooks, custom gradle tasks, annotation processors).
Documented attack patterns abuse exactly the kind of access build gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Android Project MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for build:
{
"version": "1",
"default": "deny",
"tools": {
"build": {
"limits": [
{
"counter": "build_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}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.
Free to start. No card required.
Build the Android project in the folder. It is categorised as a Execute tool in the Android Project MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Android Project MCP Server MCP server in PolicyLayer and add a rule for 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 Android Project MCP Server. Nothing to install.
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 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 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.
build is provided by the Android Project MCP Server MCP server (shenghaiwang/androidbuild). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Android Project MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 Android Project MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.