Browse storage volumes and import media into the Media Pool. Actions: get_volumes() -> {volumes} get_subfolders(path) -> {subfolders} get_files(path) -> {files} reveal(path) -> {success} import_to_pool(items) -> {imported} — simple: params.items is a list of absolute file/folder paths import_to_p...
AI agents use media_storage 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 primary risky actions are importing media into the Media Pool (Write - creating new entries in the project) and browsing storage (Read). The import operations add clips/mattes to the project but are generally reversible by removing them. The most severe applicable category is Write. Browsing/reveal actions are Read-level but the tool as a whole is classified by its highest-severity action.
From the tool's definition 'import media into the Media Pool', 'import_to_pool(items) -> {imported}', 'import_to_pool(item_infos) -> {imported}'
Documented attack patterns abuse exactly the kind of access media_storage 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_storage:
{
"version": "1",
"default": "deny",
"tools": {
"media_storage": {
"limits": [
{
"counter": "media_storage_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}media_storage 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.
Browse storage volumes and import media into the Media Pool. Actions: get_volumes() -> {volumes} get_subfolders(path) -> {subfolders} get_files(path) -> {files} reveal(path) -> {success} import_to_pool(items) -> {imported} — simple: params.items is a list of absolute file/folder paths import_to_pool(item_infos) -> {imported} — positioned: params.item_infos is a list of {media, startFrame, endFrame} dicts per docs line 210. Mirrors MediaStorage.AddItemListToMediaPool([{itemInfo}, ...]). add_clip_mattes(clip_id, paths, stereo_eye?) -> {success} add_timeline_mattes(paths) -> {items}. 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_storage: 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_storage 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_storage 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_storage. 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_storage 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.