AI agents use resolve_create_subtitles 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 new subtitle data on a timeline, which is a reversible modification operation. It doesn't execute arbitrary code, delete data, or move money. The severity is medium because an AI agent could misuse it to add unwanted subtitles to projects, but the damage is reversible and the blast radius is limited to a single timeline's subtitle layer.
From the tool's definition Tool name 'resolve_create_subtitles' and description 'Create auto-generated subtitles on the current timeline' explicitly states it creates/modifies timeline content by adding subtitle elements.
Attacks that exploit this kind of access
Create auto-generated subtitles on the current timeline. 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_create_subtitles: 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_create_subtitles 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_create_subtitles 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_create_subtitles. 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_create_subtitles 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 →