AI agents use resolve_apply_arri_cdl_lut to create or update resources in Resolve — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Resolve environment.
The tool creates or modifies color grading information (CDL=Color Decision List, LUT=Look-Up Table) on a clip, which is reversible editing work. It does not execute arbitrary code, delete data permanently, or move money. While it affects the project state, color grading changes are typical Write operations in non-linear editing.
From the tool's definition Tool name includes 'apply' and description states 'Apply ARRI CDL and LUT to the current clip's grade' — this modifies color grading data on a clip.
Attacks that exploit this kind of access
Apply ARRI CDL and LUT to the current clip's grade. It is categorised as a Write tool in the Resolve MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Resolve MCP server in PolicyLayer and add a rule for resolve_apply_arri_cdl_lut: 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 Resolve. Nothing to install.
resolve_apply_arri_cdl_lut 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 resolve_apply_arri_cdl_lut 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 resolve_apply_arri_cdl_lut. 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.
resolve_apply_arri_cdl_lut is provided by the Resolve MCP server (jenkinsm13/resolve-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 →