AI agents use update_project_uids to create or update resources in Godot MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Godot MCP environment.
The tool modifies UIDs (unique identifiers) in Godot project resources by resaving them. This is a write operation because it changes project data, but it's reversible (UIDs can be regenerated or corrected in subsequent operations). It doesn't delete data irreversibly (Destructive), execute arbitrary code (Execute), or transfer funds (Financial).
From the tool's definition Tool description states 'Update UID references in a Godot project by resaving resources' — this modifies project data through resource resaving, which is a reversible write operation.
Attacks that exploit this kind of access
Update UID references in a Godot project by resaving resources (for Godot 4.4+). It is categorised as a Write tool in the Godot MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Godot MCP server in PolicyLayer and add a rule for update_project_uids: 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 MCP. Nothing to install.
update_project_uids 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 update_project_uids 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 update_project_uids. 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.
update_project_uids is provided by the Godot MCP server (jamesdowzard/godot-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 →