AI agents use open_project to create or update resources in SK Wwise MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SK Wwise MCP environment.
Opening a project file constitutes a state change in the Wwise environment—it switches the active project and loads associated resources. This is a reversible operation (you can open a different project or close it), so it does not qualify as Destructive. It is Write rather than Execute because the operation is narrowly scoped to project file loading rather than executing arbitrary code or commands.
From the tool's definition Tool description: 'Open a Wwise project file.' The tool modifies the state of the Wwise authoring environment by loading a project, which changes the currently active project context and may trigger initialization of project-related data structures.
Documented attack patterns abuse exactly the kind of access open_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SK Wwise MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for open_project:
{
"version": "1",
"default": "deny",
"tools": {
"open_project": {
"limits": [
{
"counter": "open_project_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}open_project stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Open a Wwise project file. It is categorised as a Write tool in the SK Wwise MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SK Wwise MCP server in PolicyLayer and add a rule for open_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 SK Wwise MCP. Nothing to install.
open_project is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the open_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 open_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.
open_project is provided by the SK Wwise MCP server (silver-rain-dev/sk-wwise-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SK Wwise MCP, 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.
98 SK Wwise MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.