Apply a unified diff patch on a new git branch
AI agents use apply_patch to create or update resources in Godot Sentinel MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Godot Sentinel MCP environment.
This tool modifies code files by applying patches, making it a Write action rather than Read. It does not irreversibly delete data (so not Destructive), nor does it execute arbitrary code directly (so not Execute—though patches can contain significant changes).
From the tool's definition Tool applies a unified diff patch on a git branch, modifying file contents. The description confirms it performs patch application, which creates or modifies data.
Attacks that exploit this kind of access
Apply a unified diff patch on a new git branch. It is categorised as a Write tool in the Godot Sentinel MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Godot Sentinel MCP server in PolicyLayer and add a rule for apply_patch: 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 Godot Sentinel MCP. Nothing to install.
apply_patch 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 apply_patch 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 apply_patch. 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.
apply_patch is provided by the Godot Sentinel MCP server (snack-jpg/godot-sentinel-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 →