AI agents invoke resolve_regenerate_magic_mask to trigger actions in Resolve. 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.
Regenerating a Magic Mask triggers a computational operation on an existing clip in DaVinci Resolve, processing and overwriting a previously generated mask. This is an Execute action as it runs an external operation (mask regeneration) whose effects depend on the clip and its settings. It modifies state but is likely reversible via undo, so not Destructive.
From the tool's definition Regenerate the Magic Mask on a timeline clip
Attacks that exploit this kind of access
Regenerate the Magic Mask on a timeline clip. It is categorised as a Execute tool in the Resolve MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Resolve MCP server in PolicyLayer and add a rule for resolve_regenerate_magic_mask: 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_regenerate_magic_mask 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 resolve_regenerate_magic_mask 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_regenerate_magic_mask. 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_regenerate_magic_mask 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 →