Cloud project operations (requires DaVinci Resolve cloud infrastructure). Actions: create(settings) -> {success} — settings: {CLOUD_SETTING_PROJECT_NAME, ...} load(settings) -> {success} import_project(path, settings) -> {success} restore(folder_path, settings) -> {success}
AI agents use project_manager_cloud 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.
This tool modifies cloud project state through create, import, and restore actions. While these operations are reversible (projects can be deleted or overwritten), they have significant blast radius if misused by an AI agent—an agent could create numerous unwanted projects, import malicious project files, or restore old versions destructively overwriting current work.
From the tool's definition The tool provides create, load, import_project, and restore actions that modify cloud project state. Specifically, create(settings) and import_project(path, settings) create new projects or import existing ones into cloud storage, and restore(folder_path,…
Documented attack patterns abuse exactly the kind of access project_manager_cloud 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 project_manager_cloud:
{
"version": "1",
"default": "deny",
"tools": {
"project_manager_cloud": {
"limits": [
{
"counter": "project_manager_cloud_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}project_manager_cloud 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.
Cloud project operations (requires DaVinci Resolve cloud infrastructure). Actions: create(settings) -> {success} — settings: {CLOUD_SETTING_PROJECT_NAME, ...} load(settings) -> {success} import_project(path, settings) -> {success} restore(folder_path, settings) -> {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 project_manager_cloud: 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.
project_manager_cloud 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 project_manager_cloud 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 project_manager_cloud. 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.
project_manager_cloud 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.