AI agents call shader_read to retrieve information from MCP Server for Unity without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads/retrieves shader files from a Unity project. It performs a query-like operation that does not modify, execute, or delete any data. The 'read' verb and retrieval nature of the operation clearly indicate a Read category classification. Even though shaders could theoretically contain sensitive code, the tool itself has no capability to execute or modify anything - it merely fetches data.
From the tool's definition Tool name is 'shader_read' and description states 'Read a shader from Unity project' - this is a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access shader_read gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Server for Unity, and nothing reaches the server without passing your rules. This is the rule we recommend for shader_read:
{
"version": "1",
"default": "deny",
"tools": {
"shader_read": {}
}
}shader_read is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read a shader from Unity project. It is categorised as a Read tool in the MCP Server for Unity MCP Server, which means it retrieves data without modifying state.
Register the MCP Server for Unity MCP server in PolicyLayer and add a rule for shader_read: 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 MCP Server for Unity. Nothing to install.
shader_read is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the shader_read 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 shader_read. 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.
shader_read is provided by the MCP Server for Unity MCP server (zabaglione/mcp-server-unity). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Server for Unity, 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.
15 MCP Server for Unity tools catalogued and risk-classified — across an index of 43,000+ MCP servers.