AI agents call get_runtime_spawns to retrieve information from Unity without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves information about existing C# source code to identify where Instantiate() calls occur. It performs static analysis on source code without modifying files, executing scripts, or triggering runtime behavior. It is purely informational—analogous to a code search or grep operation. The misuse risk is minimal; an AI cannot cause damage by reading this metadata about spawn sites.
From the tool's definition Tool description states it 'Get[s] all Instantiate() call sites found in C# source' and 'Shows what scripts dynamically spawn objects at runtime.' The verb 'Get' and 'Shows' indicate retrieval/query operations with no modification of underlying data or…
Attacks that exploit this kind of access
Get all Instantiate() call sites found in C# source. Shows what scripts dynamically spawn objects at runtime. It is categorised as a Read tool in the Unity MCP Server, which means it retrieves data without modifying state.
Register the Unity MCP server in PolicyLayer and add a rule for get_runtime_spawns: 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 Unity. Nothing to install.
get_runtime_spawns 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 get_runtime_spawns 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 get_runtime_spawns. 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.
get_runtime_spawns is provided by the Unity MCP server (verysleepylemon/unity-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →