AI agents use resolve_grab_still 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.
This tool creates or stores a new media asset (a still frame) in DaVinci Resolve's gallery, which is a write operation. It does not execute arbitrary code, delete data irreversibly, move funds, or cause destructive side effects. The blast radius is minimal — the worst outcome is an unwanted still in the gallery, which can be easily removed.
From the tool's definition 'Grab a still from the current frame to the gallery' — the tool creates a new still image asset in the gallery, which is a data creation operation that is reversible (the still can be deleted).
Attacks that exploit this kind of access
Grab a still from the current frame to the gallery. 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_grab_still: 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_grab_still 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_grab_still 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_grab_still. 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_grab_still 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 →