Automatically set up the Unity Bridge for any Unity Mono game (Windows & macOS). This tool automates the full pipeline: 1. Detect: Analyzes the game folder (runtime, DLLs, architecture) 2. BepInEx: Downloads and installs BepInEx 5 mod loader 3. Build: Compiles OScribeBridge.dll adapted to the game
AI agents invoke os_unity_setup to trigger actions in OScribe. 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.
This tool performs multiple high-impact operations: downloading external software (BepInEx mod loader), installing it into a game folder, and compiling/injecting a DLL. These are external execution and write operations with significant blast radius — modifying game installations, introducing third-party code, and potentially altering system state.
From the tool's definition Automates the full pipeline: Downloads and installs BepInEx 5 mod loader, Compiles OScribeBridge.dll adapted to the game — triggers external downloads, installations, and code compilation
Attacks that exploit this kind of access
Automatically set up the Unity Bridge for any Unity Mono game (Windows & macOS). This tool automates the full pipeline: 1. Detect: Analyzes the game folder (runtime, DLLs, architecture) 2. BepInEx: Downloads and installs BepInEx 5 mod loader 3. Build: Compiles OScribeBridge.dll adapted to the game. It is categorised as a Execute tool in the OScribe MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OScribe MCP server in PolicyLayer and add a rule for os_unity_setup: 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 OScribe. Nothing to install.
os_unity_setup 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 os_unity_setup 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 os_unity_setup. 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.
os_unity_setup is provided by the OScribe MCP server (mikealkeal/oscribe). 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 →