This record as markdown: /tools/caravanglory-cocos-mcp-server/build-project.md
What build_project does on Cocos
AI agents invoke build_project to trigger actions in Cocos. 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 build_project is rated High
Building a project executes the editor's build pipeline—a complex external operation that compiles code, processes assets, and generates output artifacts. While not destructive (previous builds aren't deleted by default) or financial, it is Execute-category because it runs a defined workflow external to the MCP protocol itself.
From the tool's definition Tool name 'build_project' and description 'Build the project' indicates execution of a build process, which triggers external compilation, linking, and packaging operations whose effects depend on project configuration and build arguments.
Attacks that exploit this kind of access
The rule that runs build_project safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cocos, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For build_project, this is the rule to start with:
build_project 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Cocos, apply this rule, and every build_project call is checked against it from then on.
Questions about build_project
Build the project. It is categorised as a Execute tool in the Cocos MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cocos MCP server in PolicyLayer and add a rule for build_project: 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 Cocos. Nothing to install.
build_project 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_project 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_project. 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_project is provided by the Cocos MCP server (caravanglory/cocos-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cocos, and thousands of servers like it.
Across the catalogue