Markers and flags on media pool clips. Identify clip by clip_id. Actions: add(clip_id, frame|frame_id|frameId, color?, name?, note?, duration?, custom_data?) -> {success, frame} get_all(clip_id) -> {markers} get_by_custom_data(clip_id, custom_data) -> {markers} update_custom_data(clip_id, frame|f...
AI agents use media_pool_item_markers to create or update resources in DaVinci Resolve MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DaVinci Resolve MCP environment.
The add, update, and delete actions are reversible modifications to marker data (metadata, custom data, flags) on video clips. Markers and flags are annotations that can be undone or re-added. While delete operations are present, they target metadata annotations rather than irreversible destruction of source media or projects.
From the tool's definition Tool description states 'add()', 'update_custom_data()', and 'delete_*' actions on media pool clips. Actions include add, update, and delete operations that modify marker metadata on clips.
Documented attack patterns abuse exactly the kind of access media_pool_item_markers gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and DaVinci Resolve MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for media_pool_item_markers:
{
"version": "1",
"default": "deny",
"tools": {
"media_pool_item_markers": {
"limits": [
{
"counter": "media_pool_item_markers_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}media_pool_item_markers stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Markers and flags on media pool clips. Identify clip by clip_id. Actions: add(clip_id, frame|frame_id|frameId, color?, name?, note?, duration?, custom_data?) -> {success, frame} get_all(clip_id) -> {markers} get_by_custom_data(clip_id, custom_data) -> {markers} update_custom_data(clip_id, frame|frame_id|frameId, custom_data) -> {success} get_custom_data(clip_id, frame|frame_id|frameId) -> {data} delete_by_color(clip_id, color) -> {success} delete_at_frame(clip_id, frame|frame_id|frameId) -> {success} delete_by_custom_data(clip_id, custom_data) -> {success} add_flag(clip_id, color) -> {success} get_flags(clip_id) -> {flags} clear_flags(clip_id, color) -> {success} set_name(clip_id, name) -> {success} link_full_resolution_media(clip_id, path) -> {success} monitor_growing_file(clip_id) -> {success} replace_clip_preserve_sub_clip(clip_id, path) -> {success}. It is categorised as a Write tool in the DaVinci Resolve MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the DaVinci Resolve MCP server in PolicyLayer and add a rule for media_pool_item_markers: 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 DaVinci Resolve MCP. Nothing to install.
media_pool_item_markers 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 media_pool_item_markers 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 media_pool_item_markers. 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.
media_pool_item_markers is provided by the DaVinci Resolve MCP server (samuelgursky/davinci-resolve-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 369 DaVinci Resolve MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
369 DaVinci Resolve MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.